HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

TMLR Paper5980 Authors

Abstract:

An Achilles heel of Large Language Models (LLMs) is their tendency to hallucinate non-factual statements. A response mixed of factual and non-factual statements poses a challenge for humans to verify and accurately base their decisions on. To combat this problem, we propose Highlighted Chain-of-Thought Prompting (HoT), a technique for prompting LLMs to generate responses with XML tags that ground facts to those provided in the question. That is, given an input question, LLMs would first re-format the question to add XML tags
highlighting key facts, and then, generate a response with highlights over the facts referenced from the input. Compared to vanilla chain of thought prompting (CoT), HoT reduces the rate of hallucination and separately improves LLM accuracy of 5 LLMs consistently on over 22 tasks from arithmetic, reading comprehension, to logical reasoning.
Consistent with the success of HoT few-shot prompting, training small LLMs (LLaMA-3.2-1B and Qwen2.5-1.5B) via supervised-finetuning on HoT examples improve LLMs accuracy (on 5 out-of-distribution tasks) over the baselines and over finetuning on CoT examples. When asking humans to verify LLM responses, highlights help time-limited participants to more accurately and efficiently recognize when LLMs are correct. Yet, surprisingly, when LLMs are wrong, HoTs tend to fool users into believing that an answer is correct.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Kamalika_Chaudhuri1

Submission Number: 5980