paper-with-me

홈 › Papers

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

2023-05-07 · NeurIPS 2023 11 · Miles Turpin, Julian Michael, Ethan Perez, Samuel R. Bowman

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM's process for solving a task. This level of transparency into LLMs' predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model's prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs--e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always "(A)"--which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods.

📄 PDF Abstract BibTeX arXiv:2305.04388

Code (2)

milesaturpin/cot-unfaithfulness 공식 구현
kmatton/walk-the-talk

Tasks

Multiple-choice

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Multi-Head Attention 설명 없음
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

2025-03-11 · Iván Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan 외

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful, i.e. CoT reasoning does not always reflect how m…

Perks and Pitfalls of Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs

2024-06-21 · Steve Azzolin, Antonio Longa, Stefano Teso, Andrea Passerini

As Graph Neural Networks (GNNs) become more pervasive, it becomes paramount to build robust tools for computing explanations of their predictions. A key desideratum is that these explanations are faithful, i.e., that the…

InformativenessOut-of-Distribution Generalization

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

2025-08-27 · Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras arxiv

Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We i…

Show or Tell? Demonstration is More Robust to Changes in Shared Perception than Explanation

2020-12-16 · Theodore R. Sumers, Mark K. Ho, Thomas L. Griffiths

Successful teaching entails a complex interaction between a teacher and a learner. The teacher must select and convey information based on what they think the learner perceives and believes. Teaching always involves misa…

Dissociation of Faithful and Unfaithful Reasoning in LLMs

2024-05-23 · Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung 외

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thou…