paper-with-me

홈 › Papers

Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models

2024-10-03 · Yinhong Liu, Zhijiang Guo, Tianya Liang, Ehsan Shareghi, Ivan Vulić, Nigel Collier

Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistency as a foundational requirement for building more dependable LLM systems, ensuring stable and coherent decision-making while minimizing erratic or contradictory outputs. To quantify the logical preference consistency, we propose a universal evaluation framework based on three fundamental properties: transitivity, commutativity and negation invariance. Through extensive experimentation across diverse LLMs, we demonstrate that these properties serve as strong indicators of judgment robustness. Furthermore, we introduce a data refinement and augmentation technique, REPAIR, that enhances logical consistency while maintaining alignment with human preferences. Finally, we show that improving consistency leads to better performance in LLM-driven logic-based algorithms, reinforcing stability and coherence in decision-making systems.

📄 PDF Abstract BibTeX arXiv:2410.02205

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingNegation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up

2024-10-16 · Jiahao Yuan, Dehui Du, Hao Zhang, Zixiang Di 외

Large language models (LLMs) have shown remarkable performance in reasoning tasks but face limitations in mathematical and complex logical reasoning. Existing methods to improve LLMs' logical capabilities either involve …

VRM: Teaching Reward Models to Understand Authentic Human Preferences

2026-03-05 · Biao Liu, Ning Xu, Junming Yang, Hao Xu 외 arxiv

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches pre…

Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts

2018-03-12 · Faisal Alshargi, Saeedeh Shekarpour, Tommaso Soru, Amit Sheth

Although there is an emerging trend towards generating embeddings for primarily unstructured data and, recently, for structured data, no systematic suite for measuring the quality of embeddings has been proposed yet. Thi…

ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis

2026-03-19 · Zhan Jin, Yu Luo, Yizhou Zhang, Ziyang Cui 외 arxiv

Conventional pixel-wise loss functions fail to enforce topological constraints in coronary vessel segmentation, producing fragmented vascular trees despite high pixel-level accuracy. We present ARIADNE, a two-stage frame…

Evaluating Morphological Plausibility of Subword Tokenization via Statistical Alignment with Morpho-Syntactic Features

2026-01-26 · Abishek Stephen, Jindřich Libovický arxiv

We present a novel metric for the evaluation of the morphological plausibility of subword segmentation. Unlike the typically used morpheme boundary or retrieval F-score, which requires gold segmentation data that is eith…