paper-with-me

Papers

Self-Training Meets Consistency: Improving LLMs' Reasoning With Consistency-Driven Rationale Evaluation

2024-11-10 · JaeHyeok Lee, Keisuke Sakaguchi, JinYeong Bak

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as appropriate for training. However, a single measure risks misjudging rationale quality, leading the models to learn flawed reasoning patterns. To address this issue, we propose CREST (Consistency-driven Rationale Evaluation for Self-Training), a self-training framework that further evaluates each rationale through follow-up questions and leverages this evaluation to guide its training. Specifically, we introduce two methods: (1) filtering out rationales that frequently result in incorrect answers on follow-up questions and (2) preference learning based on mixed preferences from rationale evaluation results of both original and follow-up questions. Experiments on three question-answering datasets using open LLMs show that CREST not only improves the logical robustness and correctness of rationales but also improves reasoning abilities compared to previous self-training approaches.

📄 PDF Abstract BibTeX arXiv:2411.06387

Code (1)

jaehyeoklee-119/crest 공식 구현 pytorch

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models

2025-04-02 · Zhiwei Yu, Tuo Li, Changhong Wang, Hui Chen 외

Chain-of-thought (CoT) has emerged as a critical mechanism for enhancing reasoning capabilities in large language models (LLMs), with self-consistency demonstrating notable promise in boosting performance. However, inher…

Math

Improving Self Consistency in LLMs through Probabilistic Tokenization

2024-07-04 · Ashutosh Sathe, Divyanshu Aggarwal, Sunayana Sitaram

Prior research has demonstrated noticeable performance gains through the use of probabilistic tokenizations, an approach that involves employing multiple tokenizations of the same input string during the training phase o…

Language ModelingLanguage Modelling

Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection

2025-04-13 · MingShan Liu, Shi Bo, Jialing Fang

Large language models (LLMs) have demonstrated strong mathematical reasoning capabilities but remain susceptible to hallucinations producing plausible yet incorrect statements especially in theorem proving, symbolic mani…

Answer SelectionAutomated Theorem ProvingComputational EfficiencyHallucination+1

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging

2024-04-19 · Chia-Hsuan Chang, Mary M. Lucas, Yeawon Lee, Christopher C. Yang 외

Advances in large language models (LLMs) have encouraged their adoption in the healthcare domain where vital clinical information is often contained in unstructured notes. Cancer staging status is available in clinical r…

Language ModelingLanguage ModellingLarge Language Model

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs

2023-05-23 · Angelica Chen, Jason Phang, Alicia Parrish, Vishakh Padmakumar 외

Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is …

valid