AICLAug 30, 2022

Faithful Reasoning Using Large Language Models

arXiv:2208.14271v1157 citationsh-index: 50
Originality Incremental advance
AI Analysis

This addresses the need for more transparent and effective reasoning in AI systems, particularly for complex multi-step problems, though it is incremental as it builds on existing LM capabilities.

The paper tackles the problem of opaque and low-performance single-step reasoning in large language models by introducing a method for faithful multi-step reasoning that chains fine-tuned models for selection and inference, resulting in improved accuracy on logical deduction and scientific question-answering tasks.

Although contemporary large language models (LMs) demonstrate impressive question-answering capabilities, their answers are typically the product of a single call to the model. This entails an unwelcome degree of opacity and compromises performance, especially on problems that are inherently multi-step. To address these limitations, we show how LMs can be made to perform faithful multi-step reasoning via a process whose causal structure mirrors the underlying logical structure of the problem. Our approach works by chaining together reasoning steps, where each step results from calls to two fine-tuned LMs, one for selection and one for inference, to produce a valid reasoning trace. Our method carries out a beam search through the space of reasoning traces to improve reasoning quality. We demonstrate the effectiveness of our model on multi-step logical deduction and scientific question-answering, showing that it outperforms baselines on final answer accuracy, and generates humanly interpretable reasoning traces whose validity can be checked by the user.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes