Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal
摘要
Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge is either unavailable to the LLM or not up-to-date within its parameters. While using the question to retrieve relevant text from an external knowledge source helps LLMs, we observe that this one-step retrieve-and-read approach is insufficient for multi-step QA. Here, what to retrieve depends on what has already been derived, which in turn may depend on what was previously retrieved. To address this, we propose IRCoT, a new approach for multi-step QA that interleaves retrieval with steps (sentences) in a CoT, guiding the retrieval with CoT and in turn using retrieved results to improve CoT. Using IRCoT with GPT3 substantially improves retrieval (up to 21 points) as well as downstream QA (up to 15 points) on four datasets: HotpotQA, 2WikiMultihopQA, MuSiQue, and IIRC. We observe similar substantial gains in out-ofdistribution (OOD) settings as well as with much smaller models such as Flan-T5-large without additional training. IRCoT reduces model hallucination, resulting in factually more accurate CoT reasoning. 1 . A: The actor that stars as Joe Proctor on the series "Power" is Jerry Ferrara. Jerry Ferrara also played a character on Entourage named Turtle Assante. Thus, Turtle Assante's last name is Assante. So the answer is: Assante. Q: Nobody Loves You was written by John Lennon and released on what album that was issued by Apple Records, and was written, recorded, and released during his 18 month separation from Yoko Ono? A: The album issued by Apple Records, and written, recorded, and released during John Lennon's 18 month separation from Yoko Ono is Walls and Bridges. Nobody Loves You was written by John Lennon on Walls and Bridges album. So the answer is: Walls and Bridges.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper260
- A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei, Hang Gao 等NeurIPS 2025 · 被引用 1,138 次
- Benchmarking Large Language Models in Retrieval-Augmented GenerationJiawei Chen, Hongyu Lin, Xianpei Han, Le SunAAAI 2024 · 被引用 531 次
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga 等NeurIPS 2024 · 被引用 395 次
- Making Retrieval-Augmented Language Models Robust to Irrelevant ContextOri Yoran, Tomer Wolfson, Ori Ram, Jonathan BerantICLR 2024 · 被引用 361 次
- RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMsYue Yu, Wei Ping, Zihan Liu, Boxin Wang 等NeurIPS 2024 · 被引用 321 次
它引用的顶会 Paper16
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida 等NeurIPS 2022 · 被引用 24,707 次
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni 等NeurIPS 2020 · 被引用 19,162 次
- Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat 等ICML 2020 · 被引用 2,937 次
相关 Paper
- ERA-CoT: Improving Chain-of-Thought through Entity Relationship AnalysisYanming Liu, Xinyue Peng, Tianyu Du, Jianwei Yin 等ACL 2024 · 被引用 18 次
- Unveiling Factual Recall Behaviors of Large Language Models through Knowledge NeuronsYifei Wang, Yuheng Chen, Wanting Wen, Yu Sheng 等EMNLP 2024 · 被引用 3 次
- INFORM : Information eNtropy based multi-step reasoning FOR large language ModelsChuyue Zhou, Wangjie You, Juntao Li, Jing Ye 等EMNLP 2023 · 被引用 2 次
- Interleaved-Modal Chain-of-ThoughtJun Gao, Yongqi Li, Ziqiang Cao, Wenjie LiCVPR 2025
- Large Language Models Can Self-ImproveJiaxin Huang, Shixiang Gu, Le Hou, Yuexin Wu 等EMNLP 2023 · 被引用 184 次
