-
Notifications
You must be signed in to change notification settings - Fork 28
/
bibtex.bib
16997 lines (16067 loc) · 631 KB
/
bibtex.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@inproceedings{DBLP:conf:acl:ChenZZK022,
author = {Yanda Chen and
Ruiqi Zhong and
Sheng Zha and
George Karypis and
He He},
editor = {Smaranda Muresan and
Preslav Nakov and
Aline Villavicencio},
title = {Meta-learning via Language Model In-context Tuning},
booktitle = {ACL},
pages = {719--730},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.acl-long.53},
doi = {10.18653/v1/2022.acl-long.53},
timestamp = {Mon, 01 Aug 2022 16:27:45 +0200},
biburl = {https://dblp.org/rec/conf/acl/ChenZZK022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords = {In-Context Learning, Meta Learning},
plm={BERT, DeBERTa, GPT-2}
}
@string(DBLP:conf:acl:ChenZZK022="This paper proposes in-context tuning, which recasts task adaptation and prediction as a simple sequence prediction problem: to form the input sequence, concatenate the task instruction, labeled in-context examples, and the target input to predict; to meta train the model to learn from in-context examples, finetune a PLM to predict the target label given the input sequence on a collection of tasks (very similar to MetaICL). On LAMA and BinaryClfs, the proposed method outperforms MAML.")
@article{DBLP:journals/corr/abs-2210-12810,
author = {Xingyao Wang and
Sha Li and
Heng Ji},
title = {Code4Struct: Code Generation for Few-Shot Structured Prediction from
Natural Language},
journal = {CoRR},
volume = {abs/2210.12810},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.12810},
doi = {10.48550/arXiv.2210.12810},
eprinttype = {arXiv},
eprint = {2210.12810},
timestamp = {Fri, 28 Oct 2022 14:21:57 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-12810.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords = {Program and Code Generation}
}
@inproceedings{DBLP:conf/cvpr/0002ZL0SRSPDP22,
author = {Zifeng Wang and
Zizhao Zhang and
Chen{-}Yu Lee and
Han Zhang and
Ruoxi Sun and
Xiaoqi Ren and
Guolong Su and
Vincent Perot and
Jennifer G. Dy and
Tomas Pfister},
title = {Learning to Prompt for Continual Learning},
booktitle = {CVPR},
pages = {139--149},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/CVPR52688.2022.00024},
doi = {10.1109/CVPR52688.2022.00024},
timestamp = {Tue, 04 Oct 2022 17:56:08 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/0002ZL0SRSPDP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords = {Continual Learning, Prompt Engineering}
}
@inproceedings{DBLP:conf/emnlp/Hu0X0SO22,
author = {Yushi Hu and
Chia{-}Hsuan Lee and
Tianbao Xie and
Tao Yu and
Noah A. Smith and
Mari Ostendorf},
editor = {Yoav Goldberg and
Zornitsa Kozareva and
Yue Zhang},
title = {In-Context Learning for Few-Shot Dialogue State Tracking},
booktitle = {Findings of the Association for Computational Linguistics: {EMNLP}
2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
pages = {2627--2643},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://aclanthology.org/2022.findings-emnlp.193},
timestamp = {Tue, 07 Feb 2023 17:10:51 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/Hu0X0SO22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/GuptaJYMEB22,
author = {Prakhar Gupta and
Cathy Jiao and
Yi{-}Ting Yeh and
Shikib Mehri and
Maxine Esk{\'{e}}nazi and
Jeffrey P. Bigham},
editor = {Yoav Goldberg and
Zornitsa Kozareva and
Yue Zhang},
title = {InstructDial: Improving Zero and Few-shot Generalization in Dialogue
through Instruction Tuning},
booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates,
December 7-11, 2022},
pages = {505--525},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://aclanthology.org/2022.emnlp-main.33},
timestamp = {Tue, 07 Feb 2023 17:10:51 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/GuptaJYMEB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-07128,
author = {Aman Madaan and
Shuyan Zhou and
Uri Alon and
Yiming Yang and
Graham Neubig},
title = {Language Models of Code are Few-Shot Commonsense Learners},
journal = {CoRR},
volume = {abs/2210.07128},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.07128},
doi = {10.48550/arXiv.2210.07128},
eprinttype = {arXiv},
eprint = {2210.07128},
timestamp = {Tue, 18 Oct 2022 15:06:52 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-07128.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords = {Program and Code Generation}
}
@inproceedings{DBLP:conf/naacl/WebsonP22,
author = {Albert Webson and
Ellie Pavlick},
editor = {Marine Carpuat and
Marie{-}Catherine de Marneffe and
Iv{\'{a}}n Vladimir Meza Ru{\'{\i}}z},
title = {Do Prompt-Based Models Really Understand the Meaning of Their Prompts?},
booktitle = {NAACL},
pages = {2300--2344},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.naacl-main.167},
doi = {10.18653/v1/2022.naacl-main.167},
timestamp = {Mon, 01 Aug 2022 16:28:03 +0200},
biburl = {https://dblp.org/rec/conf/naacl/WebsonP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords= {Prompt Engineering}
}
@inproceedings{DBLP:conf:naacl:MinLZH22,
author = {Sewon Min and
Mike Lewis and
Luke Zettlemoyer and
Hannaneh Hajishirzi},
editor = {Marine Carpuat and
Marie{-}Catherine de Marneffe and
Iv{\'{a}}n Vladimir Meza Ru{\'{\i}}z},
title = {MetaICL: Learning to Learn In Context},
booktitle = {NAACL},
pages = {2791--2809},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.naacl-main.201},
doi = {10.18653/v1/2022.naacl-main.201},
timestamp = {Mon, 01 Aug 2022 16:28:01 +0200},
biburl = {https://dblp.org/rec/conf/naacl/MinLZH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords= {In-Context Learning, Meta Learning},
code={https://github.com/facebookresearch/MetaICL},
plm={GPT-2}
}
@string(DBLP:conf:naacl:MinLZH22="MetaICL proposes a supervised meta-training framework to enable LMs to more effectively learn a new task in context. In MetaICL, each meta-training example includes several training examples from one task that will be presented together as a single sequence to the LM, and the prediction of the final example is used to calculate the loss.")
@article{DBLP:journals/corr/abs-2209-12356,
author = {Tanya Goyal and
Junyi Jessy Li and
Greg Durrett},
title = {News Summarization and Evaluation in the Era of {GPT-3}},
journal = {NeurIPS},
volume = {abs/2209.12356},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.12356},
doi = {10.48550/arXiv.2209.12356},
eprinttype = {arXiv},
eprint = {2209.12356},
timestamp = {Thu, 06 Oct 2022 14:41:30 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-12356.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={AIGC}
}
@article{DBLP:journals:corr:abs-2210-09338,
author = {Michihiro Yasunaga and
Antoine Bosselut and
Hongyu Ren and
Xikun Zhang and
Christopher D. Manning and
Percy Liang and
Jure Leskovec},
title = {Deep Bidirectional Language-Knowledge Graph Pretraining},
journal = {NeurIPS},
volume = {abs/2210.09338},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.09338},
doi = {10.48550/arXiv.2210.09338},
eprinttype = {arXiv},
eprint = {2210.09338},
timestamp = {Mon, 24 Oct 2022 18:10:06 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-09338.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Knowledge Enhanced,Knowledge Graph Embedding}
}
@article{DBLP:journals:corr:abs-2209-01975,
author = {Hongjin Su and
Jungo Kasai and
Chen Henry Wu and
Weijia Shi and
Tianlu Wang and
Jiayi Xin and
Rui Zhang and
Mari Ostendorf and
Luke Zettlemoyer and
Noah A. Smith and
Tao Yu},
title = {Selective Annotation Makes Language Models Better Few-Shot Learners},
journal = {CoRR},
volume = {abs/2209.01975},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.01975},
doi = {10.48550/arXiv.2209.01975},
eprinttype = {arXiv},
eprint = {2209.01975},
timestamp = {Tue, 27 Sep 2022 08:13:21 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-01975.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Selective Annotation, In-Context Learning},
code={https://github.com/HKUNLP/icl-selective-annotation},
plm={SBERT, GPT-J, GPT-Neo, GPT-3, Codex, OPT}
}
@String(DBLP:journals:corr:abs-2209-01975="This paper proposes a graph-based selective annotation method named vote-k to
(1) select a pool of examples to annotate from unlabeled data,
(2) retrieve prompts (contexts) from the annotated data pool for in-context learning.
Specifically, the selection method first selects a small set of unlabeled examples iteratively and then labels them to serve as contexts for LLMs to predict the labels of the rest unlabeled data. The method selects the predictions with highest confidence (log probability of generation output) to fill up the selective annotation pool.")
@article{DBLP:journals/pvldb/ChaiLTLL22,
author = {Chengliang Chai and
Jiabin Liu and
Nan Tang and
Guoliang Li and
Yuyu Luo},
title = {Selective Data Acquisition in the Wild for Model Charging},
journal = {VLDB},
volume = {15},
number = {7},
pages = {1466--1478},
year = {2022},
url = {https://www.vldb.org/pvldb/vol15/p1466-li.pdf},
timestamp = {Wed, 29 Jun 2022 11:10:54 +0200},
biburl = {https://dblp.org/rec/journals/pvldb/ChaiLTLL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Selective Annotation}
}
@article{DBLP:journals/corr/abs-2212-09420,
author = {Daoguang Zan and
Bei Chen and
Fengji Zhang and
Dianjie Lu and
Bingchao Wu and
Bei Guan and
Yongji Wang and
Jian{-}Guang Lou},
title = {When Neural Model Meets NL2Code: {A} Survey},
journal = {CoRR},
volume = {abs/2212.09420},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.09420},
doi = {10.48550/arXiv.2212.09420},
eprinttype = {arXiv},
eprint = {2212.09420},
timestamp = {Tue, 03 Jan 2023 15:59:43 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-09420.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Program and Code Generation, Survey}
}
@article{DBLP:journals:corr:abs-2212-13428,
author = {Chaoqi Zhen and
Yanlei Shang and
Xiangyu Liu and
Yifei Li and
Yong Chen and
Dell Zhang},
title = {A Survey on Knowledge-Enhanced Pre-trained Language Models},
journal = {TKDE},
volume = {abs/2212.13428},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.13428},
doi = {10.48550/arXiv.2212.13428},
eprinttype = {arXiv},
eprint = {2212.13428},
timestamp = {Wed, 04 Jan 2023 16:01:37 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-13428.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Knowledge Enhanced, Survey}
}
@article{yi2022review,
title={Review of Knowledge-Enhanced Pre-trained Language Models},
author={Yi, HAN and Linbo, QIAO and Dongsheng, LI and Xiangke, LIAO},
journal={FCST},
volume={16},
number={7},
pages={1439},
year={2022},
url={https://doi.org/10.3778/j.issn.1673-9418.2108105},
keywords={Knowledge Enhanced}
}
@article{DBLP:journals:corr:abs-2302-04023,
author = {Yejin Bang and
Samuel Cahyawijaya and
Nayeon Lee and
Wenliang Dai and
Dan Su and
Bryan Wilie and
Holy Lovenia and
Ziwei Ji and
Tiezheng Yu and
Willy Chung and
Quyet V. Do and
Yan Xu and
Pascale Fung},
title = {A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning,
Hallucination, and Interactivity},
journal = {CoRR},
volume = {abs/2302.04023},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.04023},
doi = {10.48550/arXiv.2302.04023},
eprinttype = {arXiv},
eprint = {2302.04023},
timestamp = {Fri, 10 Feb 2023 12:26:38 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-04023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Evaluation}
}
@String(DBLP:journals:corr:abs-2302-04023="本文提出了一个使用公开数据集定量评估交互式LLM(如ChatGPT)的框架。我们使用涵盖8个不同的常见NLP应用任务的21个数据集对ChatGPT进行了广泛的技术评估。我们基于这些数据集和一个新设计的多模态数据集评估了ChatGPT的多任务、多语言和多模态方面。")
@article{DBLP:journals:corr:abs-2301-12810,
author = {Roi Cohen and
Mor Geva and
Jonathan Berant and
Amir Globerson},
title = {Crawling the Internal Knowledge-Base of Language Models},
journal = {EACL},
volume = {abs/2301.12810},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.12810},
doi = {10.48550/arXiv.2301.12810},
eprinttype = {arXiv},
eprint = {2301.12810},
timestamp = {Wed, 01 Feb 2023 14:38:31 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-12810.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Knowledge Generation}
}
@String(DBLP:journals:corr:abs-2301-12810="本文提出一种从语言模型中提取结构化知识图谱的方法;使用专门设计的提示来控制提取过程中的精度和召回率;在GPT-3上进行了评估,显示了高精确度的结果。")
@article{DBLP:journals/corr/abs-2211-09110,
author = {Percy Liang and
Rishi Bommasani and
Tony Lee and
Dimitris Tsipras and
Dilara Soylu and
Michihiro Yasunaga and
Yian Zhang and
Deepak Narayanan and
Yuhuai Wu and
Ananya Kumar and
Benjamin Newman and
Binhang Yuan and
Bobby Yan and
Ce Zhang and
Christian Cosgrove and
Christopher D. Manning and
Christopher R{\'{e}} and
Diana Acosta{-}Navas and
Drew A. Hudson and
Eric Zelikman and
Esin Durmus and
Faisal Ladhak and
Frieda Rong and
Hongyu Ren and
Huaxiu Yao and
Jue Wang and
Keshav Santhanam and
Laurel J. Orr and
Lucia Zheng and
Mert Y{\"{u}}ksekg{\"{o}}n{\"{u}}l and
Mirac Suzgun and
Nathan Kim and
Neel Guha and
Niladri S. Chatterji and
Omar Khattab and
Peter Henderson and
Qian Huang and
Ryan Chi and
Sang Michael Xie and
Shibani Santurkar and
Surya Ganguli and
Tatsunori Hashimoto and
Thomas Icard and
Tianyi Zhang and
Vishrav Chaudhary and
William Wang and
Xuechen Li and
Yifan Mai and
Yuhui Zhang and
Yuta Koreeda},
title = {Holistic Evaluation of Language Models},
journal = {CoRR},
volume = {abs/2211.09110},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.09110},
doi = {10.48550/arXiv.2211.09110},
eprinttype = {arXiv},
eprint = {2211.09110},
timestamp = {Wed, 23 Nov 2022 18:03:56 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-09110.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Evaluation}
}
@article{DBLP:journals/corr/abs-2302-00923,
author = {Zhuosheng Zhang and
Aston Zhang and
Mu Li and
Hai Zhao and
George Karypis and
Alex Smola},
title = {Multimodal Chain-of-Thought Reasoning in Language Models},
journal = {CoRR},
volume = {abs/2302.00923},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.00923},
doi = {10.48550/arXiv.2302.00923},
eprinttype = {arXiv},
eprint = {2302.00923},
timestamp = {Thu, 09 Feb 2023 16:11:17 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-00923.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Chain of Thought}
}
@article{DBLP:journals:corr:abs-2301-00303,
author = {Hangfeng He and
Hongming Zhang and
Dan Roth},
title = {Rethinking with Retrieval: Faithful Large Language Model Inference},
journal = {CoRR},
volume = {abs/2301.00303},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.00303},
doi = {10.48550/arXiv.2301.00303},
eprinttype = {arXiv},
eprint = {2301.00303},
timestamp = {Tue, 10 Jan 2023 15:10:12 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-00303.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Chain of Thought}
}
@String(DBLP:journals:corr:abs-2301-00303="本文通过用GPT-3在三个复杂的推理任务:常识推理,时间推理和表格推理上进行大量实验来评估RR的有效性。结果表明,RR可以产生更忠实的解释,并提高LLM的性能。")
@inproceedings{DBLP:conf/aaai/VilaresSSG20,
author = {David Vilares and
Michalina Strzyz and
Anders S{\o}gaard and
Carlos G{\'{o}}mez{-}Rodr{\'{\i}}guez},
title = {Parsing as Pretraining},
booktitle = {AAAI},
pages = {9114--9121},
publisher = {{AAAI} Press},
year = {2020},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/6446},
timestamp = {Mon, 07 Mar 2022 16:57:52 +0100},
biburl = {https://dblp.org/rec/conf/aaai/VilaresSSG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Others}
}
// from Chen Yongrui
@article{DBLP:journals/corr/abs-2107-03374,
author = {Mark Chen and
Jerry Tworek and
Heewoo Jun and
Qiming Yuan and
Henrique Pond{\'{e}} de Oliveira Pinto and
Jared Kaplan and
Harrison Edwards and
Yuri Burda and
Nicholas Joseph and
Greg Brockman and
Alex Ray and
Raul Puri and
Gretchen Krueger and
Michael Petrov and
Heidy Khlaaf and
Girish Sastry and
Pamela Mishkin and
Brooke Chan and
Scott Gray and
Nick Ryder and
Mikhail Pavlov and
Alethea Power and
Lukasz Kaiser and
Mohammad Bavarian and
Clemens Winter and
Philippe Tillet and
Felipe Petroski Such and
Dave Cummings and
Matthias Plappert and
Fotios Chantzis and
Elizabeth Barnes and
Ariel Herbert{-}Voss and
William Hebgen Guss and
Alex Nichol and
Alex Paino and
Nikolas Tezak and
Jie Tang and
Igor Babuschkin and
Suchir Balaji and
Shantanu Jain and
William Saunders and
Christopher Hesse and
Andrew N. Carr and
Jan Leike and
Joshua Achiam and
Vedant Misra and
Evan Morikawa and
Alec Radford and
Matthew Knight and
Miles Brundage and
Mira Murati and
Katie Mayer and
Peter Welinder and
Bob McGrew and
Dario Amodei and
Sam McCandlish and
Ilya Sutskever and
Wojciech Zaremba},
title = {Evaluating Large Language Models Trained on Code},
journal = {CoRR},
volume = {abs/2107.03374},
year = {2021},
url = {https://arxiv.org/abs/2107.03374},
eprinttype = {arXiv},
eprint = {2107.03374},
timestamp = {Thu, 09 Feb 2023 14:04:35 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-03374.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Evaluation, Program and Code Generation}
}
@article{DBLP:journals/corr/abs-2301-12868,
author = {Terry Yue Zhuo and
Zhuang Li and
Yujin Huang and
Yuan{-}Fang Li and
Weiqing Wang and
Gholamreza Haffari and
Fatemeh Shiri},
title = {On Robustness of Prompt-based Semantic Parsing with Large Pre-trained
Language Model: An Empirical Study on Codex},
journal = {CoRR},
volume = {abs/2301.12868},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.12868},
doi = {10.48550/arXiv.2301.12868},
eprinttype = {arXiv},
eprint = {2301.12868},
timestamp = {Fri, 03 Feb 2023 10:27:08 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-12868.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Prompt Engineering, Program and Code Generation}
}
@inproceedings{DBLP:conf/iclr/LiuSPGSKS18,
author = {Peter J. Liu and
Mohammad Saleh and
Etienne Pot and
Ben Goodrich and
Ryan Sepassi and
Lukasz Kaiser and
Noam Shazeer},
title = {Generating Wikipedia by Summarizing Long Sequences},
booktitle = {ICLR},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=Hyg0vbWC-},
timestamp = {Thu, 25 Jul 2019 14:25:42 +0200},
biburl = {https://dblp.org/rec/conf/iclr/LiuSPGSKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={AIGC}
}
@article{radford2018improving,
title={Improving language understanding by generative pre-training},
author={Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya and others},
url = {https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf},
year = {2018},
booktitle = {OpenAI},
keywords = {AIGC, Natural Language Understanding, Pre-Training Techniques},
plm={GPT-1}
}
@article{radfordlanguage,
title={Language Models are Unsupervised Multitask Learners},
author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
url = {https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf},
year = {2019},
booktitle = {OpenAI},
plm ={GPT-2},
keywords = {AIGC, Pre-Training Techniques}
}
@inproceedings{DBLP:conf/nips/BrownMRSKDNSSAA20,
author = {Tom B. Brown and
Benjamin Mann and
Nick Ryder and
Melanie Subbiah and
Jared Kaplan and
Prafulla Dhariwal and
Arvind Neelakantan and
Pranav Shyam and
Girish Sastry and
Amanda Askell and
Sandhini Agarwal and
Ariel Herbert{-}Voss and
Gretchen Krueger and
Tom Henighan and
Rewon Child and
Aditya Ramesh and
Daniel M. Ziegler and
Jeffrey Wu and
Clemens Winter and
Christopher Hesse and
Mark Chen and
Eric Sigler and
Mateusz Litwin and
Scott Gray and
Benjamin Chess and
Jack Clark and
Christopher Berner and
Sam McCandlish and
Alec Radford and
Ilya Sutskever and
Dario Amodei},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Language Models are Few-Shot Learners},
booktitle = {NeurIPS},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html},
timestamp = {Tue, 19 Jan 2021 15:56:50 +0100},
biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Pre-Training Techniques, AIGC},
plm={GPT-3}
}
@article{DBLP:journals:corr:abs-2301-00234,
author = {Qingxiu Dong and
Lei Li and
Damai Dai and
Ce Zheng and
Zhiyong Wu and
Baobao Chang and
Xu Sun and
Jingjing Xu and
Lei Li and
Zhifang Sui},
title = {A Survey for In-context Learning},
journal = {CoRR},
volume = {abs/2301.00234},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.00234},
doi = {10.48550/arXiv.2301.00234},
eprinttype = {arXiv},
eprint = {2301.00234},
timestamp = {Tue, 10 Jan 2023 15:10:12 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-00234.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={In-Context Learning, Survey}
}
@String(DBLP:journals:corr:abs-2301-00234="This paper surveys and summarizes the progress and challenges of ICL, including ICL's formal definition, correlation to related studies, advanced techniques (training strategies, related analysis) and potential directions.")
@inproceedings{DBLP:conf:naacl:ChenDPMISK22,
author = {Mingda Chen and
Jingfei Du and
Ramakanth Pasunuru and
Todor Mihaylov and
Srini Iyer and
Veselin Stoyanov and
Zornitsa Kozareva},
editor = {Marine Carpuat and
Marie{-}Catherine de Marneffe and
Iv{\'{a}}n Vladimir Meza Ru{\'{\i}}z},
title = {Improving In-Context Few-Shot Learning via Self-Supervised Training},
booktitle = {NAACL},
pages = {3558--3573},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.naacl-main.260},
doi = {10.18653/v1/2022.naacl-main.260},
timestamp = {Mon, 01 Aug 2022 16:27:58 +0200},
biburl = {https://dblp.org/rec/conf/naacl/ChenDPMISK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={In-Context Learning},
plm={MoE}
}
@string(DBLP:conf:naacl:ChenDPMISK22="This paper proposes to use self-supervision (MLM, NSP, CL, etc.) between pre-training and downstream usage to teach the LM to perform in-context learning. Analysis reveals that:
(1) benefits of self-supervised depends on the amount of training data,
(2) semantic similarity between training and evaluation tasks matters,
(3) adding training objectives without diversity does not help,
(4) model performance improves when choosing similar templates for both self-supervised and downstream tasks,
(5) self-supervised tasks and human-annotated datasets are complementary,
(6) self-supervised-trained models are better at following task instructions.")
@inproceedings{DBLP:conf/iclr/WeiBZGYLDDL22,
author = {Jason Wei and
Maarten Bosma and
Vincent Y. Zhao and
Kelvin Guu and
Adams Wei Yu and
Brian Lester and
Nan Du and
Andrew M. Dai and
Quoc V. Le},
title = {Finetuned Language Models are Zero-Shot Learners},
booktitle = {ICLR},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=gEZrGCozdqR},
timestamp = {Sat, 20 Aug 2022 01:15:42 +0200},
biburl = {https://dblp.org/rec/conf/iclr/WeiBZGYLDDL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Instruction Tuning}
}
@article{DBLP:journals/corr/abs-2201-08239,
author = {Romal Thoppilan and
Daniel De Freitas and
Jamie Hall and
Noam Shazeer and
Apoorv Kulshreshtha and
Heng{-}Tze Cheng and
Alicia Jin and
Taylor Bos and
Leslie Baker and
Yu Du and
YaGuang Li and
Hongrae Lee and
Huaixiu Steven Zheng and
Amin Ghafouri and
Marcelo Menegali and
Yanping Huang and
Maxim Krikun and
Dmitry Lepikhin and
James Qin and
Dehao Chen and
Yuanzhong Xu and
Zhifeng Chen and
Adam Roberts and
Maarten Bosma and
Yanqi Zhou and
Chung{-}Ching Chang and
Igor Krivokon and
Will Rusch and
Marc Pickett and
Kathleen S. Meier{-}Hellstern and
Meredith Ringel Morris and
Tulsee Doshi and
Renelito Delos Santos and
Toju Duke and
Johnny Soraker and
Ben Zevenbergen and
Vinodkumar Prabhakaran and
Mark Diaz and
Ben Hutchinson and
Kristen Olson and
Alejandra Molina and
Erin Hoffman{-}John and
Josh Lee and
Lora Aroyo and
Ravi Rajakumar and
Alena Butryna and
Matthew Lamm and
Viktoriya Kuzmina and
Joe Fenton and
Aaron Cohen and
Rachel Bernstein and
Ray Kurzweil and
Blaise Aguera{-}Arcas and
Claire Cui and
Marian Croak and
Ed H. Chi and
Quoc Le},
title = {LaMDA: Language Models for Dialog Applications},
journal = {CoRR},
volume = {abs/2201.08239},
year = {2022},
url = {https://arxiv.org/abs/2201.08239},
eprinttype = {arXiv},
eprint = {2201.08239},
timestamp = {Fri, 22 Apr 2022 16:06:31 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-08239.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Instruction Tuning}
}
@article{DBLP:journals/corr/abs-2210-11416,
author = {Hyung Won Chung and
Le Hou and
Shayne Longpre and
Barret Zoph and
Yi Tay and
William Fedus and
Eric Li and
Xuezhi Wang and
Mostafa Dehghani and
Siddhartha Brahma and
Albert Webson and
Shixiang Shane Gu and
Zhuyun Dai and
Mirac Suzgun and
Xinyun Chen and
Aakanksha Chowdhery and
Sharan Narang and
Gaurav Mishra and
Adams Yu and
Vincent Y. Zhao and
Yanping Huang and
Andrew M. Dai and
Hongkun Yu and
Slav Petrov and
Ed H. Chi and
Jeff Dean and
Jacob Devlin and
Adam Roberts and
Denny Zhou and
Quoc V. Le and
Jason Wei},
title = {Scaling Instruction-Finetuned Language Models},
journal = {CoRR},
volume = {abs/2210.11416},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.11416},
doi = {10.48550/arXiv.2210.11416},
eprinttype = {arXiv},
eprint = {2210.11416},
timestamp = {Wed, 26 Oct 2022 08:16:51 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-11416.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Instruction Tuning}
}
@inproceedings{DBLP:conf/emnlp/WangMAKMNADASPK22,
author = {Yizhong Wang and
Swaroop Mishra and
Pegah Alipoormolabashi and
Yeganeh Kordi and
Amirreza Mirzaei and
Atharva Naik and
Arjun Ashok and
Arut Selvan Dhanasekaran and
Anjana Arunkumar and
David Stap and
Eshaan Pathak and
Giannis Karamanolakis and
Haizhi Gary Lai and
Ishan Purohit and
Ishani Mondal and
Jacob Anderson and
Kirby Kuznia and
Krima Doshi and
Kuntal Kumar Pal and
Maitreya Patel and
Mehrad Moradshahi and
Mihir Parmar and
Mirali Purohit and
Neeraj Varshney and
Phani Rohitha Kaza and
Pulkit Verma and
Ravsehaj Singh Puri and
Rushang Karia and
Savan Doshi and
Shailaja Keyur Sampat and
Siddhartha Mishra and
Sujan Reddy A and
Sumanta Patro and
Tanay Dixit and
Xudong Shen},
editor = {Yoav Goldberg and
Zornitsa Kozareva and
Yue Zhang},
title = {Super-NaturalInstructions: Generalization via Declarative Instructions
on 1600+ {NLP} Tasks},
booktitle = {EMNLP},
pages = {5085--5109},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://aclanthology.org/2022.emnlp-main.340},
timestamp = {Tue, 07 Feb 2023 17:10:51 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/WangMAKMNADASPK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Instruction Tuning}
}
@article{DBLP:journals:corr:abs-2205-10782,
author = {Or Honovich and
Uri Shaham and
Samuel R. Bowman and
Omer Levy},
title = {Instruction Induction: From Few Examples to Natural Language Task
Descriptions},
journal = {CoRR},
volume = {abs/2205.10782},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.10782},
doi = {10.48550/arXiv.2205.10782},
eprinttype = {arXiv},
eprint = {2205.10782},
timestamp = {Mon, 09 Jan 2023 08:11:56 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-10782.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={In-Context Learning, Chain of Thought},
}
@String(DBLP:journals:corr:abs-2205-10782="(1) 探索了利用LLM在几个样本的情况下归纳出任务指令的能力;
(2) 测量两个指标:1. 模型归纳指令与人类归纳的指令对比,2. 利用模型归纳的指令作为prompt进行预测的执行准确率;
(3) 相比于GPT-3,InstructGPT效果更好,理所当然。")
@article{DBLP:journals/corr/abs-2211-01910,
author = {Yongchao Zhou and
Andrei Ioan Muresanu and
Ziwen Han and
Keiran Paster and
Silviu Pitis and
Harris Chan and
Jimmy Ba},
title = {Large Language Models Are Human-Level Prompt Engineers},
journal = {CoRR},
volume = {abs/2211.01910},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.01910},
doi = {10.48550/arXiv.2211.01910},
eprinttype = {arXiv},
eprint = {2211.01910},
timestamp = {Fri, 04 Nov 2022 13:48:49 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-01910.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Prompt Engineering}
}
@article{DBLP:journals/corr/abs-2212-10560,
author = {Yizhong Wang and
Yeganeh Kordi and
Swaroop Mishra and
Alisa Liu and
Noah A. Smith and
Daniel Khashabi and
Hannaneh Hajishirzi},
title = {Self-Instruct: Aligning Language Model with Self Generated Instructions},
journal = {CoRR},
volume = {abs/2212.10560},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.10560},
doi = {10.48550/arXiv.2212.10560},
eprinttype = {arXiv},
eprint = {2212.10560},
timestamp = {Wed, 04 Jan 2023 16:01:37 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-10560.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
keywords={Instruction Tuning}