20 results for “Explicit reasoning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Guancheng Tu, Xiangjun Fu, Suhao Yu, Yao Tang +4 more
This paper proposes NF-CoT, a latent reasoning framework that preserves the advantages of chain-of-thought in large language models.
Renfei Dang, Xinye Wang, Zhejian Lai, Weilu Xu +4 more
The paper proposes RIEQE, a two-stage training framework that synergistically co-evolves implicit and explicit reasoning capabilities in Large Reasoning Models (LRMs) to significantly improve fine-gra…
One clear sentence describing what this paper does
Zhicheng Hui, Lihan Xie, Xingzhi Qi, Zhehao Li +2 more
The paper introduces Relaxed Natural Formal Language (Relaxed NFL) as an intermediate target for auto-formalization to bridge the gap between informal mathematical writing and formal proof languages.
This paper investigates the properties of code interpretation in large language models and proposes methods to improve reasoning capabilities.
Dingling Xu, Ruobing Wang, Qingfei Zhao, Yukun Yan +7 more
The paper proposes CheckRLM, a framework that improves the reliability of Reasoning Language Models by identifying and correcting factual errors using Retrieval-Augmented Generation.
This paper resolves the expressiveness conundrum between Iris and Indirection Theory by showing that Indirection Theory can be as expressive as Iris.
Yaoming Li, Guangxiang Zhao, Qilong Shi, Lin Sun +2 more
This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…
This paper presents the theory of Eigenius, a store of typed knowledge over constructive institutions.
The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…
The paper establishes a formal relationship between abstract interpretations and a general class of effect systems.
This paper proposes Chained Recursive Language Models (Chained RLM), an inference-time architecture for managing context in large language models, allowing for intermediate artifacts to be inspected,…
The paper introduces a new evaluation method for chain-of-thought controllability and shows that models can achieve higher controllability when constraints are placed inside the model's chain-of-thoug…
This paper introduces a fuzzy-logic-based qualitative extension of Answer Set Programming (ASP) to integrate numerical information and qualitative reasoning.
The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…
Improves accuracy and reduces generation length of large language models
Jiening Siow, Hanrui Zuo, Hanyun Jiang, Weiqi Wang +1 more
This paper studies and compares three strategies for solving shared-context batched satisfiability in program analyzers.