%0 Generic %1 he2022rethinking %A He, Hangfeng %A Zhang, Hongming %A Roth, Dan %D 2022 %K llm retrieval %T Rethinking with Retrieval: Faithful Large Language Model Inference %U http://arxiv.org/abs/2301.00303 %X Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting. This lightweight approach does not require additional training or fine-tuning and is not limited by the input length of LLMs. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks: commonsense reasoning, temporal reasoning, and tabular reasoning. Our results show that RR can produce more faithful explanations and improve the performance of LLMs.

@misc{he2022rethinking, abstract = {Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting. This lightweight approach does not require additional training or fine-tuning and is not limited by the input length of LLMs. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks: commonsense reasoning, temporal reasoning, and tabular reasoning. Our results show that RR can produce more faithful explanations and improve the performance of LLMs.}, added-at = {2023-08-17T15:00:13.000+0200}, author = {He, Hangfeng and Zhang, Hongming and Roth, Dan}, biburl = {https://www.bibsonomy.org/bibtex/228dc13cb9071cc2b9c07893298939fe3/lisa-ee}, description = {Rethinking with Retrieval: Faithful Large Language Model Inference}, interhash = {9b3be74c72df8a6b0771efb41be3e894}, intrahash = {28dc13cb9071cc2b9c07893298939fe3}, keywords = {llm retrieval}, note = {cite arxiv:2301.00303}, timestamp = {2023-08-17T15:00:13.000+0200}, title = {Rethinking with Retrieval: Faithful Large Language Model Inference}, url = {http://arxiv.org/abs/2301.00303}, year = 2022 }