语言大模型 / LLM

Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering

Ander Salaberria, Gorka Azkune, Oier Lopez de Lacalle, Aitor Soroa, Eneko Agirre

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.AI

Comments Under review. 25 pages with 4 figures

Journal ref Expert Systems with Applications, Volume 212, 2023, 118669

Limitations of Language Models in Arithmetic and Symbolic Induction

Jing Qian, Hong Wang, Zekun Li, Shiyang Li, Xifeng Yan

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Rationale-Augmented Ensembles in Language Models

Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Denny Zhou

专题命中 推理与问题求解 ：language model(title)；prompting(abstract)；分类 cs.CL

Knowledge-Augmented Language Models for Cause-Effect Relation Classification

Pedram Hosseini, David A. Broniatowski, Mona Diab

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments Accepted to Commonsense Representation and Reasoning (CSRR) @ ACL 2022

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

Albert Q. Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygóźdź, Piotr Miłoś, Yuhuai Wu, Mateja Jamnik

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.AI

Predicting Human Psychometric Properties Using Computational Language Models

Antonio Laverghetta, Animesh Nighojkar, Jamshidbek Mirzakhalov, John Licato

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments To appear in Quantitative Psychology, The 86th Annual Meeting of the Psychometric Society, Virtual. arXiv admin note: substantial text overlap with arXiv:2106.06849

Developmental Negation Processing in Transformer Language Models

Antonio Laverghetta, John Licato

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments To appear as a short paper at ACL 2022

minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models

Kanishka Misra

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments To be submitted; Code to reproduce experiments can be found on https://github.com/kanishkamisra/minicons-experiments

KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models

Daniel Gao, Yantao Jia, Lei Li, Chengzhen Fu, Zhicheng Dou, Hao Jiang, Xinyu Zhang, Lei Chen, Zhao Cao

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

On Language Model Integration for RNN Transducer based Speech Recognition

Wei Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments accepted at ICASSP2022

LanguageRefer: Spatial-Language Model for 3D Visual Grounding

Junha Roh, Karthik Desingh, Ali Farhadi, Dieter Fox

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments 11 pages, 3 figures

Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models

Tassilo Klein, Moin Nabi

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments To appear at EMNLP 2021

A Transformer-based Math Language Model for Handwritten Math Expression Recognition

Huy Quang Ung, Cuong Tuan Nguyen, Hung Tuan Nguyen, Thanh-Nghia Truong, Masaki Nakagawa

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments 14 pages, accepted in ICDAR-DIL 2021

DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation

Xinyu Hua, Ashwin Sreevatsa, Lu Wang

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments Accepted at ACL 2021. Project page: https://xinyuhua.github.io/Resources/acl21/

REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training

Fangkai Jiao, Yangyang Guo, Yilin Niu, Feng Ji, Feng-Lin Li, Liqiang Nie

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments 14 pages, 3 figures, Findings of ACL 2021

Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries

Benjamin Heinzerling, Kentaro Inui

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments EACL 2021

Functorial Language Models

Alexis Toumi, Alex Koziell-Pipe

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments Submitted to SemSpace 2021

Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions

Peter A. Jansen

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments Accepted to Findings of EMNLP. V2: corrected typo Table 1; margins Table 3

Injecting Numerical Reasoning Skills into Language Models

Mor Geva, Ankit Gupta, Jonathan Berant

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments ACL 2020

Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

Paweł Budzianowski, Ivan Vulić

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Explain Yourself! Leveraging Language Models for Commonsense Reasoning

Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, Richard Socher

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Comments Accepted at ACL, 11 pages total

Journal ref In Proceedings of the Association for Computational Linguistics (ACL), 2019. Florence, Italy

Towards an Improved Performance Measure for Language Models

Joerg P. Ueberla

专题命中 推理与问题求解 ：language model(title,abstract)；分类 cs.CL

Testing Refactoring Engine via Historical Bug Report driven LLM

Haibo Wang, Zhuolin Xu, Shin Hwei Tan

专题命中 推理与问题求解 ：LLM(title,abstract)；foundation model(comments)

Comments Accepted at the 2nd ACM international conference on AI Foundation Models and Software Engineering (FORGE 2025)

SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers

SymbolLKG：基于逻辑知识图谱与符号求解器的可验证逻辑推理研究

Haizhao Fan, Yuchi Xiong, Jize Wang, Xinping Guan, Xinyi Le

机构 * Shanghai JiaoTong University（上海交通大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

AI总结 该研究针对大型语言模型逻辑推理的缺陷，提出结合逻辑知识图谱与动态求解器路由的神经-符号架构，在基准任务上优于现有方法，实现了可验证的高准确率逻辑推理。

Comments 19 pages, 9 figures

Decoupled Physical Modeling and Execution for Physics Reasoning

用于物理推理的解耦物理建模与执行

Ye Zhang, Xuehang Guo, Rui Pan, Pengfei Yu, Denghui Zhang, Manling Li, Qingyun Wang

机构 * University of Pennsylvania（宾夕法尼亚大学） ； William & Mary（威廉玛丽学院） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Amazon（亚马逊公司） ； Stevens Institute of Technology（史蒂文斯理工学院） ； Northwestern University（西北大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；post-training(abstract)；分类 cs.CL、cs.LG

AI总结 该研究提出解耦物理建模与执行的统一框架，通过两阶段后训练策略提升小型大语言模型物理推理性能，在多个基准上实现约3%的平均性能提升。

ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning

ChainPrune：评估与减少长思维链推理中的冗余

Weihang Pan, Zhengxu Yu, Yuxiang Zhang, Wenzhi Li, Zhongming Jin, Binbin Lin, Xiaofei He, Jieping Ye

机构 * Alibaba Group（阿里巴巴集团） 纠错

专题命中 推理与问题求解 ：LLM(abstract_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

AI总结 ChainPrune 是一种推理路径语义结构优化方法，通过整合推理路径为树结构、选择主导路径及结合 DPO 与监督损失，减少长思维链冗余，在保精度的同时降低了步骤长度与计算开销。

Comments 15 pages, 12 figures, 4 tables

When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness

解释何时能帮助上下文学习？自然语言解释类型与忠实度的比较研究

Mahdi Dhaini, Adam Dejl, Juraj Vladika, Volkan Özer, Barbara Plank, Gjergji Kasneci

机构 * LMU Munich（慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Imperial College London（伦敦帝国学院） ； Technical University of Munich（慕尼黑工业大学） ； MaiNLP lab, CIS, LMU Munich（慕尼黑大学CIS研究所MaiNLP实验室） 纠错

专题命中 推理与问题求解 ：LLM(abstract,abstract_cn)；prompting(abstract)；分类 cs.CL、cs.AI

AI总结 该研究通过在6个基准和4个指令调优模型上的比较评估，探究不同来源与选择方式的自然语言解释对上下文学习下游性能的影响，为实际提示流程中解释的选择和报告提供了见解。

STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering

STAIR：用于时间问答中可解释推理的语义-时间自动机

Xinlong Dai, Jinchuan Zhang, Lei Gao, Xinzhe Hu, Yuefeng He, Hui Gao

专题命中 推理与问题求解 ：LLM(abstract,abstract_cn)；pretraining(abstract)；分类 cs.CL、cs.AI

AI总结 本文提出STAIR语义-时间自动机，将语义解读与时间推理分离，规则优先设计减少自由推理，在多个时间问答数据集上优于基线，提升了F1值且可解释性更强。

Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity

Ping Chen, Xiang Liu, Zhaoxiang Liu, Zezhou Chen, Xingpeng Zhang, Huan Hu, Zipeng Wang, Kai Wang, Shuming Shi, Shiguo Lian

机构 * Data Science & AI Research Institute, China Unicom（中国unicom数据科学与人工智能研究院） ； Unicom Data Intelligence, China Unicom（中国unicom数据智能） ； School of Computer Science and Software Engineering, Southwest Petroleum University（西南石油大学计算机科学与软件工程学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepet by EMNLP 2025 Findings (11 pages, 1 figures)

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025, pages 10230-10240, Suzhou, China. Association for Computational Linguistics

Claim-Level Reliability Assessment for Efficient Test-Time Reasoning

面向高效测试时推理的声明级可靠性评估

Sen Xu, Wei Wang, Shixi Liu, Jixin Min, Yingwei Dai, Zhibin Yin, Yirong Chen, Junlin Zhang

机构 * Sina Weibo Inc.（新浪微博公司） 纠错

专题命中 推理与问题求解 ：LLM(summary_cn,abstract_cn)；分类 cs.CL、cs.AI

AI总结 本研究提出无需训练的CLR框架，将测试时计算从解决方案采样重分配至声明级语义证伪，在匹配预算下于四个LLM及四个推理基准上提升了推理性能，减少了标记使用量。