|
5 | 5 | <div style="line-height:0.2em;">
|
6 | 6 |
|
7 | 7 |
|
| 8 | +[**Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning**](https://arxiv.org/abs/2406.16989) (**2024.06.24**) |
| 9 | + |
| 10 | +<font color="gray">Ziyu Zhao, Leilei Gan, Guoyin Wang, Yuwei Hu, Tao Shen, etc </font> |
| 11 | + |
| 12 | + |
| 13 | + |
| 14 | +--- |
| 15 | + |
| 16 | +[**Enhancing RAG Systems: A Survey of Optimization Strategies for Performance and Scalability**](https://doi.org/10.55041/ijsrem35402) (**2024.06.04**) |
| 17 | + |
| 18 | +<font color="gray">【INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT】</font> |
| 19 | + |
| 20 | + |
| 21 | + |
| 22 | +--- |
| 23 | + |
| 24 | +[**Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training**](https://doi.org/10.48550/arXiv.2405.20978) (**2024.05.31**) |
| 25 | + |
| 26 | +<font color="gray">Feiteng Fang, Yuelin Bai, Shiwen Ni, Min Yang, Xiaojun Chen, etc . - 【arXiv.org】</font> |
| 27 | + |
| 28 | + |
| 29 | + |
| 30 | +--- |
| 31 | + |
| 32 | +[**Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection**](https://doi.org/10.48550/arXiv.2405.16178) (**2024.05.25**) |
| 33 | + |
| 34 | +<font color="gray">Yun Zhu, Jia-Chen Gu, Caitlin Sikora, Ho Ko, Yinxiao Liu, etc . - 【arXiv.org】</font> |
| 35 | + |
| 36 | + |
| 37 | + |
| 38 | +--- |
| 39 | + |
| 40 | +[**DocReLM: Mastering Document Retrieval with Language Model**](https://doi.org/10.48550/arXiv.2405.11461) (**2024.05.19**) |
| 41 | + |
| 42 | +<font color="gray">Gengchen Wei, Xinle Pang, Tianning Zhang, Yu Sun, Xun Qian, etc . - 【arXiv.org】</font> |
| 43 | + |
| 44 | + |
| 45 | + |
| 46 | +--- |
| 47 | + |
| 48 | +[**UniRAG: Universal Retrieval Augmentation for Multi-Modal Large Language Models**](https://doi.org/10.48550/arXiv.2405.10311) (**2024.05.16**) |
| 49 | + |
| 50 | +<font color="gray">Sahel Sharifymoghaddam, Shivani Upadhyay, Wenhu Chen, Jimmy Lin . - 【arXiv.org】</font> |
| 51 | + |
| 52 | + |
| 53 | + |
| 54 | +--- |
| 55 | + |
| 56 | +[**ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning**](https://doi.org/10.48550/arXiv.2405.04533) (**2024.05.07**) |
| 57 | + |
| 58 | +<font color="gray">Jing Lin, Yao Feng, Weiyang Liu, Michael J. Black . - 【arXiv.org】</font> |
| 59 | + |
| 60 | + |
| 61 | + |
| 62 | +--- |
| 63 | + |
| 64 | +[**REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs**](https://doi.org/10.48550/arXiv.2405.02228) (**2024.05.03**) |
| 65 | + |
| 66 | +<font color="gray">Deepa Tilwani, Yash Saxena, Ali Mohammadi, Edward Raff, Amit P. Sheth, etc . - 【arXiv.org】</font> |
| 67 | + |
| 68 | + |
| 69 | + |
| 70 | +--- |
| 71 | + |
8 | 72 | [**Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation**](https://arxiv.org/abs/2404.06910) (**2024.04.10**)
|
9 | 73 |
|
10 | 74 | <font color="gray">Thomas Merth, Qichen Fu, Mohammad Rastegari, Mahyar Najibi </font>
|
11 | 75 |
|
12 |
| - |
| 76 | +  |
13 | 77 |
|
14 | 78 | ---
|
15 | 79 |
|
16 | 80 | [**Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models**](https://arxiv.org/abs/2404.03577) (**2024.04.04**)
|
17 | 81 |
|
18 | 82 | <font color="gray">Yan-Tie Liu, Zijun Yao, Xin Lv, Yuchen Fan, S. Cao, etc </font>
|
19 | 83 |
|
20 |
| - |
| 84 | + [](https://github.com/thu-keg/knot) |
21 | 85 |
|
22 | 86 | ---
|
23 | 87 |
|
24 | 88 | [**Unveiling LLMs: The Evolution of Latent Representations in a Temporal Knowledge Graph**](https://arxiv.org/abs/2404.03623) (**2024.04.04**)
|
25 | 89 |
|
26 | 90 | <font color="gray">Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini </font>
|
27 | 91 |
|
28 |
| - |
| 92 | +  |
| 93 | + |
| 94 | +--- |
| 95 | + |
| 96 | +[**JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning**](https://doi.org/10.48550/arXiv.2403.11366) (**2024.03.17**) |
| 97 | + |
| 98 | +<font color="gray">Anique Tahir, Lu Cheng, Huan Liu . - 【arXiv.org】</font> |
| 99 | + |
| 100 | + [](https://github.com/aniquetahir/JORA) |
29 | 101 |
|
30 | 102 | ---
|
31 | 103 |
|
32 | 104 | [**Retrieval-Augmented Generation for AI-Generated Content: A Survey**](https://arxiv.org/abs/2402.19473) (**2024.02.29**)
|
33 | 105 |
|
34 | 106 | <font color="gray">Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, etc </font>
|
35 | 107 |
|
36 |
| - |
| 108 | +  [](https://github.com/hymie122/rag-survey) |
37 | 109 |
|
38 | 110 | ---
|
39 | 111 |
|
|
45 | 117 |
|
46 | 118 | ---
|
47 | 119 |
|
| 120 | +[**The Power of Noise: Redefining Retrieval for RAG Systems**](https://doi.org/10.1145/3626772.3657834) (**2024.01.26**) |
| 121 | + |
| 122 | +<font color="gray">Florin Cuconasu, Giovanni Trappolini, F. Siciliano, Simone Filice, Cesare Campagnano, etc . - 【arXiv.org】</font> |
| 123 | + |
| 124 | +  [](https://github.com/florin-git/The-Power-of-Noise) |
| 125 | + |
| 126 | +--- |
| 127 | + |
48 | 128 | [**LLM Augmented LLMs: Expanding Capabilities through Composition**](https://doi.org/10.48550/arXiv.2401.02412) (**2024.01.04**)
|
49 | 129 |
|
50 | 130 | <font color="gray">Rachit Bansal, Bidisha Samanta, Siddharth Dalmia, Nitish Gupta, Shikhar Vashishth, etc . - 【arXiv.org】</font>
|
|
57 | 137 |
|
58 | 138 | <font color="gray">Jon Saad-Falcon, O. Khattab, Christopher Potts, Matei Zaharia . - 【arXiv.org】</font>
|
59 | 139 |
|
60 |
| - [](https://github.com/stanford-futuredata/ares) |
| 140 | + [](https://github.com/stanford-futuredata/ares) |
61 | 141 |
|
62 | 142 | ---
|
63 | 143 |
|
|
89 | 169 |
|
90 | 170 | <font color="gray">Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi . - 【arXiv.org】</font>
|
91 | 171 |
|
92 |
| - |
| 172 | + [](https://github.com/AkariAsai/self-rag) |
93 | 173 |
|
94 | 174 | ---
|
95 | 175 |
|
|
105 | 185 |
|
106 | 186 | <font color="gray">Yile Wang, Peng Li, Maosong Sun, Yang Liu . - 【Conference on Empirical Methods in Natural Language Processing】</font>
|
107 | 187 |
|
108 |
| - |
| 188 | + [](https://github.com/ruc-nlpir/flashrag) |
109 | 189 |
|
110 | 190 | ---
|
111 | 191 |
|
|
121 | 201 |
|
122 | 202 | <font color="gray">Fangyuan Xu, Weijia Shi, Eunsol Choi . - 【arXiv.org】</font>
|
123 | 203 |
|
124 |
| - [](https://github.com/carriex/recomp) |
| 204 | + [](https://github.com/carriex/recomp) |
125 | 205 |
|
126 | 206 | ---
|
127 | 207 |
|
|
137 | 217 |
|
138 | 218 | <font color="gray">Ori Yoran, Tomer Wolfson, Ori Ram, Jonathan Berant . - 【arXiv.org】</font>
|
139 | 219 |
|
140 |
| - |
| 220 | + [](https://github.com/oriyor/ret-robust) |
141 | 221 |
|
142 | 222 | ---
|
143 | 223 |
|
144 | 224 | [**RAGAS: Automated Evaluation of Retrieval Augmented Generation**](https://doi.org/10.48550/arXiv.2309.15217) (**2023.09.26**)
|
145 | 225 |
|
146 | 226 | <font color="gray">ES Shahul, Jithin James, Luis Espinosa Anke, Steven Schockaert . - 【arXiv.org】</font>
|
147 | 227 |
|
148 |
| - |
| 228 | + [](https://github.com/explodinggradients/ragas) |
149 | 229 |
|
150 | 230 | ---
|
151 | 231 |
|
152 | 232 | [**Benchmarking Large Language Models in Retrieval-Augmented Generation**](https://doi.org/10.48550/arXiv.2309.01431) (**2023.09.04**)
|
153 | 233 |
|
154 | 234 | <font color="gray">Jiawei Chen, Hongyu Lin, Xianpei Han, Le Sun . - 【arXiv.org】</font>
|
155 | 235 |
|
156 |
| - [](https://github.com/chen700564/RGB) |
| 236 | + [](https://github.com/chen700564/RGB) |
157 | 237 |
|
158 | 238 | ---
|
159 | 239 |
|
160 | 240 | [**RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models**](https://doi.org/10.48550/arXiv.2308.10633) (**2023.08.21**)
|
161 | 241 |
|
162 | 242 | <font color="gray">Yasuto Hoshi, D. Miyashita, Youyang Ng, Kento Tatsuno, Yasuhiro Morioka, etc . - 【Conference on Empirical Methods in Natural Language Processing】</font>
|
163 | 243 |
|
164 |
| - |
| 244 | + [](https://github.com/yhoshi3/ralle) |
165 | 245 |
|
166 | 246 | ---
|
167 | 247 |
|
|
201 | 281 |
|
202 | 282 | <font color="gray">Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella, Varun Manjunatha, etc </font>
|
203 | 283 |
|
204 |
| -  |
| 284 | +  |
205 | 285 |
|
206 | 286 | ---
|
207 | 287 |
|
|
281 | 361 |
|
282 | 362 | <font color="gray">Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, etc . - 【Conference on Empirical Methods in Natural Language Processing】</font>
|
283 | 363 |
|
284 |
| - [](https://github.com/jzbjyb/flare) |
| 364 | + [](https://github.com/jzbjyb/flare) |
285 | 365 |
|
286 | 366 | ---
|
287 | 367 |
|
288 | 368 | [**Augmented Large Language Models with Parametric Knowledge Guiding**](https://doi.org/10.48550/arXiv.2305.04757) (**2023.05.08**)
|
289 | 369 |
|
290 | 370 | <font color="gray">Ziyang Luo, Can Xu, Pu Zhao, Xiubo Geng, Chongyang Tao, etc . - 【arXiv.org】</font>
|
291 | 371 |
|
292 |
| - |
| 372 | + [](https://github.com/chiyeunglaw/lexlip-iccv23) |
293 | 373 |
|
294 | 374 | ---
|
295 | 375 |
|
296 | 376 | [**Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory**](https://doi.org/10.48550/arXiv.2305.02437) (**2023.05.03**)
|
297 | 377 |
|
298 | 378 | <font color="gray">Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, etc . - 【arXiv.org】</font>
|
299 | 379 |
|
300 |
| - |
| 380 | + [](https://github.com/hannibal046/selfmemory) |
301 | 381 |
|
302 | 382 | ---
|
303 | 383 |
|
|
321 | 401 |
|
322 | 402 | <font color="gray">O. Khattab, Keshav Santhanam, Xiang Lisa Li, David Leo Wright Hall, Percy Liang, etc . - 【arXiv.org】</font>
|
323 | 403 |
|
324 |
| - |
| 404 | + [](https://github.com/stanfordnlp/dsp) |
325 | 405 |
|
326 | 406 | ---
|
327 | 407 |
|
328 | 408 | [**One Embedder, Any Task: Instruction-Finetuned Text Embeddings**](https://doi.org/10.48550/arXiv.2212.09741) (**2022.12.19**)
|
329 | 409 |
|
330 | 410 | <font color="gray">Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, etc . - 【ArXiv】</font>
|
331 | 411 |
|
332 |
| - [](https://github.com/HKUNLP/instructor-embedding) |
| 412 | + [](https://github.com/HKUNLP/instructor-embedding) |
333 | 413 |
|
334 | 414 | ---
|
335 | 415 |
|
|
353 | 433 |
|
354 | 434 | <font color="gray">Zhichao Yang, Shufan Wang, Bhanu Pratap Singh Rawat, Avijit Mitra, Hong Yu . - 【Conference on Empirical Methods in Natural Language Processing】</font>
|
355 | 435 |
|
356 |
| - [](https://github.com/whaleloops/KEPT) |
| 436 | + [](https://github.com/whaleloops/KEPT) |
357 | 437 |
|
358 | 438 | ---
|
359 | 439 |
|
|
385 | 465 |
|
386 | 466 | <font color="gray">Shuyan Zhou, Uri Alon, Frank F. Xu, Zhiruo Wang, Zhengbao Jiang, etc </font>
|
387 | 467 |
|
388 |
| -  [](https://github.com/shuyanzhou/docprompting) |
| 468 | +  [](https://github.com/shuyanzhou/docprompting) |
389 | 469 |
|
390 | 470 | ---
|
391 | 471 |
|
|
401 | 481 |
|
402 | 482 | <font color="gray">Xiang Chen, Lei Li, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, etc . - 【ArXiv】</font>
|
403 | 483 |
|
404 |
| - [](https://github.com/zjunlp/promptkg) |
| 484 | + [](https://github.com/zjunlp/promptkg) |
405 | 485 |
|
406 | 486 | ---
|
407 | 487 |
|
408 | 488 | [**Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning**](https://doi.org/10.1145/3477495.3531746) (**2022.05.04**)
|
409 | 489 |
|
410 | 490 | <font color="gray">Xiang Chen, Lei Li, Ningyu Zhang, Chuanqi Tan, Fei Huang, etc . - 【Annual International ACM SIGIR Conference on Research and Development in Information Retrieval】</font>
|
411 | 491 |
|
412 |
| -  [](https://github.com/zjunlp/PromptKG/tree/main/research/RetrievalRE) |
| 492 | +  [](https://github.com/zjunlp/PromptKG/tree/main/research/RetrievalRE) |
413 | 493 |
|
414 | 494 | ---
|
415 | 495 |
|
416 | 496 | [**Contrastive Demonstration Tuning for Pre-trained Language Models**](https://doi.org/10.48550/arXiv.2204.04392) (**2022.04.09**)
|
417 | 497 |
|
418 | 498 | <font color="gray">Xiaozhuan Liang, Ningyu Zhang, Ningyu Zhang, Siyuan Cheng, Zhen Bi, etc . - 【Conference on Empirical Methods in Natural Language Processing】</font>
|
419 | 499 |
|
420 |
| - [](https://github.com/zjunlp/PromptKG/tree/main/research/Demo-Tuning) |
| 500 | + [](https://github.com/zjunlp/PromptKG/tree/main/research/Demo-Tuning) |
421 | 501 |
|
422 | 502 | ---
|
423 | 503 |
|
424 | 504 | [**Multi-Stage Prompting for Knowledgeable Dialogue Generation**](https://doi.org/10.48550/arXiv.2203.08745) (**2022.03.16**)
|
425 | 505 |
|
426 | 506 | <font color="gray">Zihan Liu, M. Patwary, R. Prenger, Shrimai Prabhumoye, Wei Ping, etc . - 【Findings】</font>
|
427 | 507 |
|
428 |
| - [](https://github.com/NVIDIA/Megatron-LM) |
| 508 | + [](https://github.com/NVIDIA/Megatron-LM) |
429 | 509 |
|
430 | 510 | ---
|
431 | 511 |
|
432 | 512 | [**Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data**](https://doi.org/10.48550/arXiv.2203.08773) (**2022.03.16**)
|
433 | 513 |
|
434 | 514 | <font color="gray">Shuo Wang, Yichong Xu, Yuwei Fang, Yang Liu, S. Sun, etc . - 【Annual Meeting of the Association for Computational Linguistics】</font>
|
435 | 515 |
|
436 |
| - [](https://github.com/microsoft/reina) |
| 516 | + [](https://github.com/microsoft/reina) |
437 | 517 |
|
438 | 518 | ---
|
439 | 519 |
|
|
457 | 537 |
|
458 | 538 | <font color="gray">Xu Han, Weilin Zhao, Ning Ding, Zhiyuan Liu, Maosong Sun . - 【AI Open】</font>
|
459 | 539 |
|
460 |
| -  [](https://github.com/thunlp/PTR) |
| 540 | +  [](https://github.com/thunlp/PTR) |
461 | 541 |
|
462 | 542 | ---
|
463 | 543 |
|
464 | 544 | [**Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks**](https://arxiv.org/abs/2005.11401) (**2020.05.22**)
|
465 | 545 |
|
466 | 546 | <font color="gray">Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, etc . - 【Neural Information Processing Systems】</font>
|
467 | 547 |
|
468 |
| -  [](https://github.com/huggingface/transformers) |
| 548 | +  [](https://github.com/huggingface/transformers) |
469 | 549 |
|
470 | 550 | ---
|
471 | 551 |
|
472 | 552 | [**REALM: Retrieval-Augmented Language Model Pre-Training**](https://arxiv.org/abs/2002.08909) (**2020.02.10**)
|
473 | 553 |
|
474 | 554 | <font color="gray">Kelvin Guu, Kenton Lee, Z. Tung, Panupong Pasupat, Ming-Wei Chang . - 【ArXiv】</font>
|
475 | 555 |
|
476 |
| -  [](https://github.com/google-research/language/tree/master/language/realm) |
| 556 | +  [](https://github.com/google-research/language/tree/master/language/realm) |
477 | 557 |
|
478 | 558 | ---
|
479 | 559 |
|
480 | 560 | [**Prompt as a Knowledge Probe for Chinese Spelling Check**](https://doi.org/10.1007/978-3-031-10989-8_41)
|
481 | 561 |
|
482 | 562 | <font color="gray">Kun Peng, Nannan Sun, Jiahao Cao, Rui Liu, Jiaqian Ren, etc . - 【Knowledge Science, Engineering and Management】</font>
|
483 | 563 |
|
484 |
| - |
| 564 | +  |
485 | 565 |
|
486 | 566 | ---
|
487 | 567 |
|
|
0 commit comments