大模型推理能力

Enhancing LLM Character-Level Manipulation via Divide and Conquer

Zhen Xiong, Yujun Cai, Bryan Hooi, Nanyun Peng, Zhecheng Li, Yiwei Wang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2

Steven Abreu, Sumit Bam Shrestha, Rui-Jie Zhu, Jason Eshraghian

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to International Conference on Learning Representations (ICLR) Workshop on Scalable Optimization for Efficient and Adaptive Foundation Models (SCOPE)

Assessing Large Language Models for Automated Feedback Generation in Learning Programming Problem Solving

Priscylla Silva, Evandro Costa

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments ICLR 2025 Oral

Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings

Michelle Elizabeth, Morgan Veyret, Miguel Couceiro, Ondrej Dusek, Lina M. Rojas-Barahona

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Scaling Large Language Model-based Multi-Agent Collaboration

Chen Qian, Zihao Xie, YiFei Wang, Wei Liu, Kunlun Zhu, Hanchen Xia, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ICLR-2025

Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery

Balaji Rama, Kai Mei, Yongfeng Zhang

专题命中 复杂问题求解 ：CoT(abstract)；分类 cs.CL、cs.AI

Comments Accepted to the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) - System Demonstration Track

Towards Understanding Graphical Perception in Large Multimodal Models

Kai Zhang, Jianwei Yang, Jeevana Priya Inala, Chandan Singh, Jianfeng Gao, Yu Su, Chenglong Wang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Work in Progress

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

Sreyan Ghosh, Sonal Kumar, Zhifeng Kong, Rafael Valle, Bryan Catanzaro, Dinesh Manocha

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted at ICLR 2025. Code and Checkpoints available here: https://github.com/Sreyan88/Synthio

Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models

Guanming Xiong, Junwei Bao, Wen Zhao

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments This work has been accepted by the ACL 2024 main conference. Code and data are available at: https://github.com/JimXiongGM/Interactive-KBQA

Graph Retrieval-Augmented LLM for Conversational Recommendation Systems

Zhangchi Qiu, Linhao Luo, Zicheng Zhao, Shirui Pan, Alan Wee-Chung Liew

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted by PAKDD 2025

Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy

Saeid Asgari Taghanaki, Joao Monteiro

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted to ICLR 2025, SSI-FM

GraphEdit: Large Language Models for Graph Structure Learning

Zirui Guo, Lianghao Xia, Yanhua Yu, Yuling Wang, Kangkang Lu, Zhiyong Huang, Chao Huang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning

Eric Zhao, Pranjal Awasthi, Nika Haghtalab

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, Tao Lin

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Update DeFT-v4, accepted by ICLR'25 (https://openreview.net/forum?id=2c7pfOqu9k). Our code is available at https://github.com/LINs-lab/DeFT

SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models

Yuxuan Zhang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments New work on PEFT for LLMs, introducing S-MagNorm and CABR-LoRA to enhance fine-tuning performance and knowledge retention. In v4, we renamed Sigmoid-based Magnitude Normalization to S-MagNorm for clarity and added a gradient comparison between SECURA and CABR-LoRA to highlight their contributions

Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis

Brian Y. Lim, Joseph P. Cahaly, Chester Y. F. Sng, Adam Chew

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments CHI 2025

Multi-LLM Collaborative Search for Complex Problem Solving

Sen Yang, Yafu Li, Wai Lam, Yu Cheng

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications

Rishi Kalra, Zekun Wu, Ayesha Gulley, Airlie Hilliard, Xin Guan, Adriano Koshiyama, Philip Treleaven

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments NAACL 2025 Industry Track & EMNLP 2024 CustomNLP4U Workshop

Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models

Alireza Amiri-Margavi, Iman Jebellat, Ehsan Jebellat, Seyed Pouyan Mousavi Davoudi

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 14 pages, 2 figures

Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model

Emre Can Acikgoz, Jeremiah Greer, Akul Datta, Ze Yang, William Zeng, Oussama Elachqar, Emmanouil Koukoumidis, Dilek Hakkani-Tür, Gokhan Tur

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs

Dongqi Fu, Liri Fang, Zihao Li, Hanghang Tong, Vetle I. Torvik, Jingrui He

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Preprint, 9 pages

Causality can systematically address the monsters under the bench(marks)

Felix Leeb, Zhijing Jin, Bernhard Schölkopf

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Assessing and Prioritizing Ransomware Risk Based on Historical Victim Data

Spencer Massengale, Philip Huff

专题命中 复杂问题求解 ：chain-of-thought(abstract)；分类 cs.AI、cs.LG

PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback

Kanika Goswami, Puneet Mathur, Ryan Rossi, Franck Dernoncourt

专题命中 复杂问题求解 ：planning(abstract)；分类 cs.CL、cs.AI

StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?

Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He, Yiting Dong, Yi Zeng

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 11 pages, 9 figures, Accepted by AAAI 2025

Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions

Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Huimin Wang, Guanhua Chen, Kam-fai Wong

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models

Zexing Xu, Zhuang Luo, Yichuan Li, Kyumin Lee, S. Rasoul Etesami

专题命中 复杂问题求解 ：self-correction(abstract)；分类 cs.CL、cs.AI

PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction

Hammad Ayyubi, Xuande Feng, Junzhang Liu, Xudong Lin, Zhecan Wang, Shih-Fu Chang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments NAACL 2025 Findings

Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks

Chang Gong, Wanrui Bian, Zhijie Zhang, Weiguo Zheng

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 24 pages