paper-with-me

Papers

Logic Agent: Enhancing Validity with Logic Rule Invocation

2024-04-28 · Hanmeng Liu, Zhiyang Teng, Chaoli Zhang, Yue Zhang

Chain-of-Thought (CoT) prompting has emerged as a pivotal technique for augmenting the inferential capabilities of language models during reasoning tasks. Despite its advancements, CoT often grapples with challenges in validating reasoning validity and ensuring informativeness. Addressing these limitations, this paper introduces the Logic Agent (LA), an agent-based framework aimed at enhancing the validity of reasoning processes in Large Language Models (LLMs) through strategic logic rule invocation. Unlike conventional approaches, LA transforms LLMs into logic agents that dynamically apply propositional logic rules, initiating the reasoning process by converting natural language inputs into structured logic forms. The logic agent leverages a comprehensive set of predefined functions to systematically navigate the reasoning process. This methodology not only promotes the structured and coherent generation of reasoning constructs but also significantly improves their interpretability and logical coherence. Through extensive experimentation, we demonstrate LA's capacity to scale effectively across various model sizes, markedly improving the precision of complex reasoning across diverse tasks.

📄 PDF Abstract BibTeX arXiv:2404.18130

Code (0)

등록된 구현이 없습니다.

Tasks

InformativenessNavigate

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Probability Logic

2019-10-15 · Niki Pfeifer

This chapter presents probability logic as a rationality framework for human reasoning under uncertainty. Selected formal-normative aspects of probability logic are discussed in the light of experimental evidence. Specif…

Descriptive

A probabilistic analysis of selected notions of iterated conditioning under coherence

2023-08-20 · Lydia Castronovo, Giuseppe Sanfilippo

It is well know that basic conditionals satisfy some desirable basic logical and probabilistic properties, such as the compound probability theorem, but checking the validity of these becomes trickier when we switch to c…

Harnessing Deep Neural Networks with Logic Rules

2016-03-21 · ACL 2016 8 · Zhiting Hu, Xuezhe Ma, Zhengzhong Liu, Eduard Hovy 외

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neur…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Sentiment Analysis

LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks

2026-02-28 · Yucheng Zeng, Weipeng Lu, Linyun Liu, Shupeng Li 외 arxiv

The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise state-transition objectives. However, t…

Reinforcement Learning

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs

2024-02-18 · Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks. However, their mastery of underlying inferential rules still falls short of human capabilities. To investigate …

Logical Reasoning