Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Rethinking with Retrieval: Faithful Large Language Model Inference

About

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in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect.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.

Hangfeng He, Hongming Zhang, Dan Roth• 2022

Related benchmarks

TaskDatasetResultRank
Commonsense ReasoningStrategyQA (test)
Accuracy77.73
81
Temporal ReasoningTempQuestions (test)
Exact Match (EM)39.05
9
Tabular ReasoningINFOTABS (dev)
Accuracy84.83
5
Showing 3 of 3 rows

Other info

Code

Follow for update