语言大模型 / LLM

Hyena Hierarchy: Towards Larger Convolutional Language Models

Michael Poli, Stefano Massaroli, Eric Nguyen, Daniel Y. Fu, Tri Dao, Stephen Baccus, Yoshua Bengio, Stefano Ermon, Christopher Ré

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

Comments Additional details

MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Ehsan Azarnasab, Faisal Ahmed, Zicheng Liu, Ce Liu, Michael Zeng, Lijuan Wang

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

Language Model Decoding as Likelihood-Utility Alignment

Martin Josifoski, Maxime Peyrard, Frano Rajic, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kıcıman, Boi Faltings, Robert West

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

Comments Accepted at EACL (Findings) 2023

COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models

Kanishka Misra, Julia Taylor Rayz, Allyson Ettinger

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

Comments EACL 2023 Camera Ready version. Code can be found at https://github.com/kanishkamisra/comps

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec

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

Comments NAACL 2021. Code & data available at https://github.com/michiyasunaga/qagnn

TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering

Yueqing Sun, Yu Zhang, Le Qi, Qi Shi

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

Comments Findings of EMNLP2022

Empowering Language Models with Knowledge Graph Reasoning for Question Answering

Ziniu Hu, Yichong Xu, Wenhao Yu, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Kai-Wei Chang, Yizhou Sun

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

Comments Published on EMNLP 2022

Investigating Math Word Problems using Pretrained Multilingual Language Models

Minghuan Tan, Lei Wang, Lingxiao Jiang, Jing Jiang

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

Comments To appear in MathNLP (The 1st Workshop on Mathematical Natural Language Processing)

NaturalProver: Grounded Mathematical Proof Generation with Language Models

Sean Welleck, Jiacheng Liu, Ximing Lu, Hannaneh Hajishirzi, Yejin Choi

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

Comments NeurIPS 2022

Mind's Eye: Grounded Language Model Reasoning through Simulation

Ruibo Liu, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, Andrew M. Dai

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

BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?

Asahi Ushio, Luis Espinosa-Anke, Steven Schockaert, Jose Camacho-Collados

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

Comments Accepted by ACL 2021 main conference

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

Wayne Xin Zhao, Kun Zhou, Zheng Gong, Beichen Zhang, Yuanhang Zhou, Jing Sha, Zhigang Chen, Shijin Wang, Cong Liu, Ji-Rong Wen

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

Comments 11 pages, Accepted by KDD 2022

TALM: Tool Augmented Language Models

Aaron Parisi, Yao Zhao, Noah Fiedel

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

Testing the Ability of Language Models to Interpret Figurative Language

Emmy Liu, Chen Cui, Kenneth Zheng, Graham Neubig

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

Comments NAACL 2022

Quantifying Adaptability in Pre-trained Language Models with 500 Tasks

Belinda Z. Li, Jane Yu, Madian Khabsa, Luke Zettlemoyer, Alon Halevy, Jacob Andreas

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

Comments NAACL 2022; 20 pages, 6 figures, 8 tables

Proof Artifact Co-training for Theorem Proving with Language Models

Jesse Michael Han, Jason Rute, Yuhuai Wu, Edward W. Ayers, Stanislas Polu

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

On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency

Seo Yeon Park, Cornelia Caragea

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

Comments Accepted at ACL 2022 main conference

GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

Xikun Zhang, Antoine Bosselut, Michihiro Yasunaga, Hongyu Ren, Percy Liang, Christopher D. Manning, Jure Leskovec

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

Comments Published at ICLR 2022. All code, data, and pretrained models are available at https://github.com/snap-stanford/GreaseLM

On Semantic Cognition, Inductive Generalization, and Language Models

Kanishka Misra

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

Comments Accepted at AAAI 2022 Doctoral Consortium

Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning

Cunxiang Wang, Boyuan Zheng, Yuchen Niu, Yue Zhang

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

Comments Accepted by NLPCC2021

Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills

Ori Yoran, Alon Talmor, Jonathan Berant

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

Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning

Bill Yuchen Lin, Seyeon Lee, Xiaoyang Qiao, Xiang Ren

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

Comments Accepted to ACL-IJCNLP 2021 (long paper at main conference). Project website: https://inklab.usc.edu/XCSR/

Prompting Contrastive Explanations for Commonsense Reasoning Tasks

Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Luke Zettlemoyer, Hannaneh Hajishirzi

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

Comments ACL 2021 Findings

ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning

Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie Zhou

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

Comments Accepted by ACL-IJCNLP 2021 main conference

Do Fine-tuned Commonsense Language Models Really Generalize?

Mayank Kejriwal, Ke Shen

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

Comments 9 pages, 2 figures

Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment

Jaap Jumelet, Willem Zuidema, Dieuwke Hupkes

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

Comments To appear at CoNLL2019

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors

VLMs需要词语：视觉语言模型倾向于通过语义锚点而非视觉细节进行推理

Haz Sameen Shahgir, Xiaofu Chen, Yu Fu, Erfan Shayegani, Nael Abu-Ghazaleh, Yova Kementchedjhieva, Yue Dong

机构 * University of California, Riverside（加州大学河滨分校） ； MBZUAI（穆桑人工智能研究院） 纠错

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

AI总结 研究发现视觉语言模型在需要细粒度视觉感知的任务中表现不佳，因其依赖语义锚点而非视觉细节。通过实验验证，模型在可命名实体上表现更佳，而Logit Lens分析显示其能恢复语义标签。任务特定微调可提升性能，无需语言先验。

Comments Accepted at the Conference on Language Modeling 2026

Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations

大语言模型代理能否应对灾难？评估异构地理空间推理在紧急行动中的基准测试

Junjue Wang, Weihao Xuan, Heli Qi, Pengyu Dai, Kunyi Liu, Hongruixuan Chen, Zhuo Zheng, Junshi Xia, Stefano Ermon, Naoto Yokoya

机构 * The University of Tokyo（东京大学） ； RIKEN AIP（理化学研究所AIP） ； Waseda University（早稻田大学） ； Stanford University（斯坦福大学） 纠错

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

AI总结 本文提出DORA基准测试，评估大语言模型在灾难响应中的端到端流程，揭示了灾难领域接地、工具选择瓶颈和组合脆弱性等挑战。

Comments DORA stress-tests LLM agents on real-world disaster operations that demand comprehensive orchestration of 108 specialized tools over heterogeneous geospatial data

Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark

基于LLM的多模态推理用于加密流量解释：一个基准

Longgang Zhang, Xiaowei Fu, Fuxiang Huang, Lei Zhang

机构 * School of Microelectronics and Communication Engineering, Chongqing University（重庆大学微电子与通信工程学院） ； School of Data Science, Lingnan University（岭南大学数据科学学院） 纠错

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

AI总结 本文提出BGTD基准和mmTraffic框架，通过结合原始字节与结构化注释，实现可解释的加密流量解释，生成高保真的人可读报告，同时保持高分类准确率。

Comments Project page \url{https://github.com/lgzhangzlg/Multimodal-Reasoning-with-LLM-for-Encrypted-Traffic-Interpretation-A-Benchmark}

None of the Others: a General Technique to Distinguish Reasoning from Memorization in Multiple-Choice LLM Evaluation Benchmarks

并非其他：一种区分推理与记忆的通用技术，用于多选LLM评估基准

Eva Sánchez Salido, Julio Gonzalo, Guillermo Marco

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

AI总结 本文提出一种通用方法，通过改变数学问题的数值来区分LLM的推理能力与记忆能力，评估了多个模型在公开和私有数据集上的表现，发现模型在该方法下准确率显著下降，揭示了记忆在当前LLM回答中的重要作用。

Journal ref "On the Limits of LLM Reasoning: Evidence From Contamination, Translation, and Answer Modification in Multiple-Choice Benchmarks," in IEEE Access, vol. 14, pp. 9384-9393, 2026