{"total":103,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56,"area":"lr"},{"id":"2410.20482","title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","created":"2024-10-27","cited_by_count":31,"area":"lr"},{"id":"2412.12932","title":"CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models","created":"2024-12-17","cited_by_count":30,"area":"lr"},{"id":"2502.13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation","created":"2025-02-18","cited_by_count":26,"area":"wm"},{"id":"2502.15844","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","created":"2025-02-20","cited_by_count":24,"area":null},{"id":"2508.19855","title":"Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning","created":"2025-08-27","cited_by_count":22,"area":"lr"},{"id":"2506.17088","title":"Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation","created":"2025-06-20","cited_by_count":21,"area":"lr"},{"id":"2406.13940","title":"AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought","created":"2024-06-20","cited_by_count":19,"area":"lr"},{"id":"2507.09876","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models","created":"2025-07-14","cited_by_count":18,"area":"lr"},{"id":"2406.08068","title":"Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey","created":"2024-06-12","cited_by_count":16,"area":null},{"id":"2508.10599","title":"Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models","created":"2025-08-14","cited_by_count":16,"area":"mechinterp"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2502.17510","title":"Recurrent Knowledge Identification and Fusion for Language Model Continual Learning","created":"2025-02-22","cited_by_count":15,"area":null},{"id":"2504.00509","title":"Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?","created":"2025-04-01","cited_by_count":15,"area":"lr"},{"id":"2409.01893","title":"What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices","created":"2024-09-03","cited_by_count":14,"area":"lr"},{"id":"2410.16670","title":"CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing","created":"2024-10-22","cited_by_count":12,"area":"lr"},{"id":"2502.17701","title":"From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2410.04463","title":"Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information","created":"2024-10-06","cited_by_count":10,"area":"lr"},{"id":"2504.20069","title":"A Simple Review of EEG Foundation Models: Datasets, Advancements and Future Perspectives","created":"2025-04-24","cited_by_count":10,"area":null},{"id":"2505.15372","title":"X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System","created":"2025-05-21","cited_by_count":10,"area":"lr"},{"id":"2408.05200","title":"KIF: Knowledge Identification and Fusion for Language Model Continual Learning","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2503.04783","title":"Comparative Analysis Based on DeepSeek, ChatGPT, and Google Gemini: Features, Techniques, Performance, Future Prospects","created":"2025-02-25","cited_by_count":9,"area":"lr"},{"id":"2508.08424","title":"Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2408.08841","title":"FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats","created":"2024-08-16","cited_by_count":8,"area":"lr"},{"id":"2501.02237","title":"Financial Named Entity Recognition: How Far Can LLM Go?","created":"2025-01-04","cited_by_count":8,"area":null},{"id":"2503.13413","title":"DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective","created":"2025-03-17","cited_by_count":8,"area":"lr"},{"id":"2505.19108","title":"CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models","created":"2025-05-25","cited_by_count":7,"area":"lr"},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2507.13859","title":"SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection","created":"2025-07-18","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2410.02613","title":"NL-Eye: Abductive NLI for Images","created":"2024-10-03","cited_by_count":5,"area":"mllm"},{"id":"2502.16358","title":"Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores","created":"2025-02-22","cited_by_count":5,"area":null},{"id":"2504.21191","title":"Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare","created":"2025-04-29","cited_by_count":5,"area":null},{"id":"2505.24174","title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2406.13443","title":"Dual-Phase Accelerated Prompt Optimization","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2412.01626","title":"WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation","created":"2024-12-02","cited_by_count":4,"area":null},{"id":"2412.18135","title":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","created":"2024-12-24","cited_by_count":4,"area":null},{"id":"2503.05551","title":"Revitalizing Saturated Benchmarks: A Weighted Metric Approach for Differentiating Large Language Model Performance","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.02579","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2505.08004","title":"Large Language Models and Arabic Content: A Review","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2505.13307","title":"RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2510.08942","title":"SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2512.24684","title":"R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory","created":"2025-12-31","cited_by_count":4,"area":"rag"},{"id":"2601.06002","title":"The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning","created":"2026-01-09","cited_by_count":4,"area":"lr"},{"id":"2603.09892","title":"MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning","created":"2026-03-10","cited_by_count":4,"area":null},{"id":"2603.21754","title":"Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts","created":"2026-03-23","cited_by_count":4,"area":"lr"},{"id":"2407.03040","title":"Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2502.00857","title":"HintEval: An Open-Source Python Toolkit for Hint Generation and Hint Evaluation","created":"2025-02-02","cited_by_count":3,"area":null},{"id":"2502.02909","title":"SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2502.15604","title":"Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance","created":"2025-02-21","cited_by_count":3,"area":"rag"},{"id":"2504.20371","title":"DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2506.13824","title":"MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2604.10332","title":"From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2412.05939","title":"Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models","created":"2024-12-08","cited_by_count":2,"area":"mllm"},{"id":"2504.01789","title":"OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models","created":"2025-04-02","cited_by_count":2,"area":"lr"},{"id":"2506.00312","title":"An evaluation of LLMs for generating movie reviews: GPT-4o, Gemini-2.0 and DeepSeek-V3","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.10330","title":"Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2509.00096","title":"Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.13790","title":"Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2509.17671","title":"Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2509.25664","title":"QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.00508","title":"Copy-Paste to Mitigate Large Language Model Hallucinations","created":"2025-10-01","cited_by_count":2,"area":"rag"},{"id":"2511.14510","title":"LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference","created":"2025-11-18","cited_by_count":2,"area":"inference"},{"id":"2512.01725","title":"Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2601.12374","title":"A Scalable Entity-Based Framework for Auditing Bias in Large Language Models","created":"2026-01-18","cited_by_count":2,"area":null},{"id":"2406.19271","title":"AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2407.20588","title":"Enhancing Agricultural Machinery Management through Advanced LLM Integration","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2412.06575","title":"Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2502.12413","title":"DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2506.16575","title":"Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System","created":"2025-06-19","cited_by_count":1,"area":"safety"},{"id":"2507.08339","title":"What Factors Affect LLMs and RLLMs in Financial Question Answering?","created":"2025-07-11","cited_by_count":1,"area":"lr"},{"id":"2509.25224","title":"AMLA: MUL by ADD in FlashAttention Rescaling","created":"2025-09-24","cited_by_count":1,"area":"inference"},{"id":"2511.21706","title":"A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2604.10159","title":"ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2604.17894","title":"Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.20090","title":"Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.00086","title":"NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2411.19689","title":"MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2501.13344","title":"Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2504.17252","title":"Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.11515","title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2507.11508","title":"Real-World Summarization: When Evaluation Reaches Its Limits","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2508.03741","title":"Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2509.00347","title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","created":"2025-08-30","cited_by_count":0,"area":"offlinerl"},{"id":"2509.05729","title":"QCSE: A Pretrained Quantum Context-Sensitive Word Embedding for Natural Language Processing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.02675","title":"HALO: Memory-Centric Heterogeneous Accelerator with 2.5D Integration for Low-Batch LLM Inference","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2511.08143","title":"Relation as a Prior: A Novel Paradigm for LLM-based Document-level Relation Extraction","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.01896","title":"OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.05004","title":"Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.04161","title":"Traces of Social Competence in Large Language Models","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.18390","title":"AutoScreen-FW: An LLM-based Framework for Resume Screening","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.17944","title":"ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.14662","title":"Scalable Solution of the Stochastic Multi-path Traveling Salesman Problem via Neural Networks","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.25263","title":"Mimir: Large-scale Multilingual Concept Modeling","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.11898","title":"GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.13624","title":"Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models","created":"2026-06-11","cited_by_count":0,"area":"inference"},{"id":"2606.22977","title":"StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":"100"}