语言大模型 / LLM

Machine Unlearning in Large Language Models

Kongyang Chen, Zixin Wang, Bing Mi, Waixi Liu, Shaowei Wang, Xiaojun Ren, Jiaxing Shen

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Leveraging Large Language Models for Multimodal Search

Oriol Barbany, Michael Huang, Xinliang Zhu, Arnab Dhua

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments Published at CVPRW 2024

Reimagining Self-Adaptation in the Age of Large Language Models

Raghav Donakanti, Prakhar Jain, Shubham Kulkarni, Karthik Vaidhyanathan

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification

Cheng Wen, Jialun Cao, Jie Su, Zhiwu Xu, Shengchao Qin, Mengda He, Haokun Li, Shing-Chi Cheung, Cong Tian

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Logical Discrete Graphical Models Must Supplement Large Language Models for Information Synthesis

Gregory Coppola

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments arXiv admin note: text overlap with arXiv:2402.06557

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, Denny Zhou

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

Comments ICLR 2024

Knowledge-Aware Code Generation with Large Language Models

Tao Huang, Zhihong Sun, Zhi Jin, Ge Li, Chen Lyu

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments Accepted in ICPC 2024

LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model

Senqiao Yang, Tianyuan Qu, Xin Lai, Zhuotao Tian, Bohao Peng, Shu Liu, Jiaya Jia

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments Typo fixed

Exploring the Potential of Large Language Models in Self-adaptive Systems

Jialong Li, Mingyue Zhang, Nianyu Li, Danny Weyns, Zhi Jin, Kenji Tei

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments accepted by SEAMS'24

Leveraging Large Language Models to Boost Dafny's Developers Productivity

Álvaro Silva, Alexandra Mendes, João F. Ferreira

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning

Jian Zhu, Hanli Wang, Miaojing Shi

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

VCoder: Versatile Vision Encoders for Multimodal Large Language Models

Jitesh Jain, Jianwei Yang, Humphrey Shi

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments Project Page: https://praeclarumjj3.github.io/vcoder/

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Lin Li, Jun Xiao, Guikun Chen, Jian Shao, Yueting Zhuang, Long Chen

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata

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

Comments Published in NeurIPS 2023 (Spotlight)

CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding

Junyan Li, Delin Chen, Yining Hong, Zhenfang Chen, Peihao Chen, Yikang Shen, Chuang Gan

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

Large Language Models are Temporal and Causal Reasoners for Video Question Answering

Dohwan Ko, Ji Soo Lee, Wooyoung Kang, Byungseok Roh, Hyunwoo J. Kim

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Comments Accepted paper at EMNLP 2023 Main

Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language Models

Mingwei Zhu, Leigang Sha, Yu Shu, Kangjia Zhao, Tiancheng Zhao, Jianwei Yin

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning

Dhruv Shah, Michael Equi, Blazej Osinski, Fei Xia, Brian Ichter, Sergey Levine

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

Comments Videos, code, and an interactive Colab notebook that runs in your browser https://sites.google.com/view/lfg-nav/

Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought

Bin Lei, pei-Hung Lin, Chunhua Liao, Caiwen Ding

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

AI Chain on Large Language Model for Unsupervised Control Flow Graph Generation for Statically-Typed Partial Code

Qing Huang, Zhou Zou, Zhenchang Xing, Zhenkang Zuo, Xiwei Xu, Qinghua Lu

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)

On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)

Karthik Valmeekam, Sarath Sreedharan, Matthew Marquez, Alberto Olmo, Subbarao Kambhampati

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

Comments arXiv admin note: text overlap with arXiv:2206.10498

PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning

PDDLCoder：用于LLM辅助符号规划的智能体式PDDL生成工具

Veit Laule, Jiangtao Shuai, Manfred Hauswirth, Sonja Schimmler

机构 * Technical University of Berlin（柏林工业大学） ； Fraunhofer FOKUS（弗劳恩霍夫FOKUS研究院） 纠错

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

AI总结 本研究提出智能体式PDDL生成框架PDDLCoder，引入含711个问题的NL-pddlgym基准，其在测试集上可生成89.6%可执行规划，优于现有方法。

FollowUpBot: An LLM-Based Conversational Robot for Automatic Postoperative Follow-up

FollowUpBot：基于大语言模型的术后自动随访对话机器人

Chen Chen, Jianing Yin, Jiannong Cao, Zhiyuan Wen, Mingjin Zhang, Weixun Gao, Xiang Wang, Haihua Shu

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

AI总结 该研究针对传统术后随访的局限，提出边缘部署的LLM机器人FollowUpBot，可实现自适应隐私保护的随访交互与结构化报告生成，实验验证其交互覆盖率、满意度及报告准确率均较高。

SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data

SemPlan：面向企业数据的基于大语言模型（LLM）查询的结构化语义规划基准测试

Bruno Santos Teixeira

机构 * Universidade Federal de Ouro Preto (UFOP)（欧鲁普雷图联邦大学（UFOP）） 纠错

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

AI总结 该研究构建了SemPlan基准测试，对比四种架构在企业数据LLM查询语义规划中的表现，发现结构化语义规划架构（A3）正确率最高，不同架构在正确率、策略合规性、成本等方面存在权衡。

Comments 11 pages, 3 figures, 9 tables. Submitted to Transactions on Machine Learning Research (TMLR)

TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems

TsuGO：通过围棋死活问题探究大语言模型推理中的搜索效率

Shunwen Bai, Ziping Ma, Chaoyang Zhang, Yarong Wang, Jiale Liu, Zhen Qin, Qingpei Guo

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

AI总结 本研究提出围棋死活问题基准TsuGO，发现现有LLM的推理搜索组织能力远逊于神经引导的KataGo，指出搜索组织是LLM推理评估的缺失维度。

Comments 23 pages, 12 figures, 20 tables, 2 algorithms

Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents

收敛式绕路劫持：基于技能的大语言模型智能体中的任务保留型资源放大

Junliang Liu, Ruoyu Li, Wenxin Tang, Jingyu Xiao, Zhenyu Liu, Jingheng Xu, Laizhong Cui

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

AI总结 该研究提出收敛式绕路劫持攻击，耦合LLM智能体技能选择与规划阶段，可放大任务资源消耗，在DeepSeek-V4-Pro上80.02%的任务会被选中攻击者控制的协调器，任务完成率不变但成本显著提升。

NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation

NetlistBench：评估大型语言模型在SPICE网表识别与操作中的可靠性

Jiarui Ma, Jianghan Wang, Yuheng Ma, Ziyi Zhuang, Xiaoguang Liu

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

AI总结 研究针对LLMs在SPICE网表识别与操作中的可靠性，构建含2342个案例的NetlistBench基准，发现其性能随结构复杂度变化，为电路设计自动化提供关键瓶颈参考。

Comments accepted by MLCAD 2026

A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems

语言模型作为形式化工具在约束满足问题上的现实检验

Rikhil Amonkar, Ceyhun Efe Kayan, Qimei Lai, Ronan Le Bras, Li Zhang

机构 * Drexel University（德雷塞尔大学） ； University of Pennsylvania（宾夕法尼亚大学） ； Allen Institute for AI（艾伦人工智能研究所） 纠错

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

AI总结 研究评估了语言模型作为形式化工具在约束满足问题中的表现，发现其在15种模型-数据集组合中表现劣于作为求解器，尽管形式化更具可验证性和可解释性。

Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction

假设前沿：验证器引导的大语言模型与符号搜索用于一阶归纳

Serafim Batzoglou

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

AI总结 本研究提出Hypothesis Frontier框架，结合LLM与符号搜索，在匹配条件下比重复原始提示生成解决更多一阶归纳问题，还可简化所得公式。

Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning

基于动态少样本学习的大语言模型预测双钙钛矿的空间群

Jongwon Park, Inhyo Lee, Junhyeong Lee, Seunghwa Ryu

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

AI总结 该研究提出基于LLM智能体的DyRIS框架，通过动态少样本检索与规则引导推理，在不平衡双钙钛矿数据集上提升了空间群预测的整体及少数类性能，验证了领域知识与LLM结合的有效性。

Comments 46 pages, 6 figures, Supplementary Information included(24 pages)