{"total":74,"rows":[{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2410.21306","title":"Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges","created":"2024-10-25","cited_by_count":42,"area":null},{"id":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2409.09822","title":"Causal Inference with Large Language Model: A Survey","created":"2024-09-15","cited_by_count":32,"area":"lr"},{"id":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31,"area":"lr"},{"id":"2502.06872","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","created":"2025-02-08","cited_by_count":30,"area":"rag"},{"id":"2505.19457","title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","created":"2025-05-26","cited_by_count":22,"area":null},{"id":"2505.17656","title":"Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2601.16669","title":"PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice","created":"2026-01-23","cited_by_count":15,"area":null},{"id":"2406.19712","title":"Uncertainty Quantification in Large Language Models Through Convex Hull Analysis","created":"2024-06-28","cited_by_count":13,"area":null},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2508.08632","title":"AgriGPT: a Large Language Model Ecosystem for Agriculture","created":"2025-08-12","cited_by_count":11,"area":"rag"},{"id":"2504.06227","title":"LExT: Towards Evaluating Trustworthiness of Natural Language Explanations","created":"2025-04-08","cited_by_count":9,"area":null},{"id":"2505.19240","title":"LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","cited_by_count":7,"area":"alignment"},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2408.15040","title":"A Survey of Large Language Models for European Languages","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2502.12421","title":"Wi-Chat: Large Language Model Powered Wi-Fi Sensing","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2507.02954","title":"Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2507.15882","title":"Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark","created":"2025-07-18","cited_by_count":6,"area":"mllm"},{"id":"2509.15087","title":"Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2604.19301","title":"Large Language Models Exhibit Normative Conformity","created":"2026-04-21","cited_by_count":6,"area":"agents"},{"id":"2506.04290","title":"Interpretable LLMs for Credit Risk: A Systematic Review and Taxonomy","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2507.20796","title":"Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach","created":"2025-07-28","cited_by_count":5,"area":"agents"},{"id":"2511.03738","title":"Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2601.06216","title":"LLM Agents in Law: Taxonomy, Applications, and Challenges","created":"2026-01-08","cited_by_count":5,"area":"agents"},{"id":"2602.00642","title":"LegalOne: A Family of Foundation Models for Reliable Legal Reasoning","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2502.18424","title":"Compressing Language Models for Specialized Domains","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2506.15846","title":"Finance Language Model Evaluation (FLaME)","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2507.18577","title":"Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2512.04578","title":"LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2409.15256","title":"Behavioral Bias of Vision-Language Models: A Behavioral Finance View","created":"2024-09-23","cited_by_count":3,"area":"mllm"},{"id":"2506.16163","title":"Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2508.19287","title":"Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2412.07261","title":"MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2501.13833","title":"On the Reasoning Capacity of AI Models and How to Quantify It","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2502.13632","title":"Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2504.15432","title":"Feeding LLM Annotations to BERT Classifiers at Your Own Risk","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2507.16514","title":"The Ever-Evolving Science Exam","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2510.00125","title":"Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning","created":"2025-09-30","cited_by_count":2,"area":"safety"},{"id":"2510.05151","title":"Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2601.03725","title":"EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2409.14050","title":"The use of GPT-4o and Other Large Language Models for the Improvement and Design of Self-Assessment Scales for Measurement of Interpersonal Communication Skills","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2502.01243","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.03080","title":"IAO Prompting: Making Knowledge Flow Explicit in LLMs through Structured Reasoning Templates","created":"2025-02-05","cited_by_count":1,"area":"lr"},{"id":"2505.00843","title":"OET: Optimization-based prompt injection Evaluation Toolkit","created":"2025-05-01","cited_by_count":1,"area":"safety"},{"id":"2510.26550","title":"EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2603.29466","title":"An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.25442","title":"PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models","created":"2026-06-24","cited_by_count":1,"area":"alignment"},{"id":"2609.14739","title":"Building Legal Reward Models for Grounding and Abstention","created":"2026-09-13","cited_by_count":1,"area":"rag"},{"id":"2411.06946","title":"Cancer-Answer: Empowering Cancer Care with Advanced Large Language Models","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2503.17963","title":"Won: Establishing Best Practices for Korean Financial NLP","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2510.03771","title":"OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2510.13106","title":"TRUSTVIS: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.16442","title":"TIB AIssistant: a Platform for AI-Supported Research Across Research Life Cycles","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2512.22174","title":"BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.06401","title":"BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2603.22340","title":"Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces","created":"2026-03-21","cited_by_count":0,"area":"rag"},{"id":"2605.07046","title":"An Interpretable and Scalable Framework for Evaluating Large Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.10593","title":"LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.21937","title":"Latent Confidence Alignment for LLM Self-Assessment","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.27047","title":"NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.01388","title":"RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.14105","title":"Automatically Evolving Prompt Guidelines for Task-Specific Optimization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.22695","title":"PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.26735","title":"Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation","created":"2026-08-27","cited_by_count":0,"area":"distill"},{"id":"2608.30683","title":"WildSEEK: Evaluating Language Models for Information-Seeking","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22537","title":"EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.04699","title":"Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}