Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback (2403.06840v2)

Published 11 Mar 2024 in cs.CL and cs.AI

Abstract: LLMs demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In The Twelfth International Conference on Learning Representations.
  2. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  4. Understanding retrieval augmentation for long-form question answering.
  5. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1–113.
  6. Time-aware language models as temporal knowledge bases. Transactions of the Association for Computational Linguistics, 10:257–273.
  7. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346–361.
  8. Retrieval augmented language model pre-training. In International conference on machine learning, pages 3929–3938. PMLR.
  9. Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625.
  10. Challenges in building intelligent open-domain dialog systems. ACM Trans. Inf. Syst., 38(3).
  11. Unsupervised dense information retrieval with contrastive learning. Transactions on Machine Learning Research.
  12. Atlas: Few-shot learning with retrieval augmented language models.
  13. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611.
  14. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781.
  15. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics, 7:453–466.
  16. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474.
  17. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9802–9822.
  18. R OpenAI. 2023. Gpt-4 technical report. arxiv 2303.08774. View in Article, 2:3.
  19. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744.
  20. Unsupervised question decomposition for question answering. arXiv preprint arXiv:2002.09758.
  21. In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083.
  22. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9248–9274, Singapore. Association for Computational Linguistics.
  23. Large language models can be easily distracted by irrelevant context. In International Conference on Machine Learning, pages 31210–31227. PMLR.
  24. Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652.
  25. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  26. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10014–10037, Toronto, Canada. Association for Computational Linguistics.
  27. Self-knowledge guided retrieval augmentation for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10303–10315, Singapore. Association for Computational Linguistics.
  28. Self-knowledge guided retrieval augmentation for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10303–10315.
  29. Recomp: Improving retrieval-augmented lms with compression and selective augmentation. arXiv preprint arXiv:2310.04408.
  30. Seqzero: Few-shot compositional semantic parsing with sequential prompts and zero-shot models. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 49–60.
  31. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369–2380.
  32. Chain-of-note: Enhancing robustness in retrieval-augmented language models. arXiv preprint arXiv:2311.09210.
  33. Least-to-most prompting enables complex reasoning in large language models. In The Eleventh International Conference on Learning Representations.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Yanming Liu (20 papers)
  2. Xinyue Peng (9 papers)
  3. Xuhong Zhang (61 papers)
  4. Weihao Liu (19 papers)
  5. Jianwei Yin (71 papers)
  6. Jiannan Cao (9 papers)
  7. Tianyu Du (34 papers)
Citations (22)
View on Semantic Scholar