{"total":128,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2405.13055","title":"Large Language Models for Medicine: A Survey","created":"2024-05-20","cited_by_count":38,"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":"2408.08089","title":"AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents","created":"2024-08-15","cited_by_count":37,"area":"agents"},{"id":"2405.13001","title":"Large Language Models for Education: A Survey","created":"2024-05-12","cited_by_count":34,"area":null},{"id":"2505.06311","title":"Defending against Indirect Prompt Injection by Instruction Detection","created":"2025-05-08","cited_by_count":32,"area":"rag"},{"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":"2405.14023","title":"WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response","created":"2024-05-22","cited_by_count":29,"area":"alignment"},{"id":"2502.05489","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","created":"2025-02-08","cited_by_count":27,"area":"mechinterp"},{"id":"2503.05683","title":"WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs","created":"2025-03-07","cited_by_count":26,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2409.00089","title":"Watermarking Techniques for Large Language Models: A Survey","created":"2024-08-26","cited_by_count":23,"area":"safety"},{"id":"2502.11191","title":"Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training","created":"2025-02-16","cited_by_count":23,"area":"distill"},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"area":"moe"},{"id":"2401.07955","title":"A Study on Large Language Models' Limitations in Multiple-Choice Question Answering","created":"2024-01-15","cited_by_count":22,"area":null},{"id":"2503.02863","title":"SteerConf: Steering LLMs for Confidence Elicitation","created":"2025-03-04","cited_by_count":20,"area":null},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2502.05196","title":"LLMs Provide Unstable Answers to Legal Questions","created":"2025-01-28","cited_by_count":19,"area":null},{"id":"2502.20640","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","created":"2025-02-28","cited_by_count":19,"area":"rag"},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"area":"moe"},{"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":"2505.19345","title":"PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims","created":"2025-05-25","cited_by_count":11,"area":null},{"id":"2406.11118","title":"Incentivizing Quality Text Generation via Statistical Contracts","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2412.20718","title":"MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models","created":"2024-12-30","cited_by_count":9,"area":"mllm"},{"id":"2502.05675","title":"Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning","created":"2025-02-08","cited_by_count":9,"area":"lr"},{"id":"2505.16113","title":"Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools","created":"2025-05-22","cited_by_count":9,"area":"agents"},{"id":"2505.16237","title":"Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation","created":"2025-05-22","cited_by_count":9,"area":"rag"},{"id":"2406.17115","title":"Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models","created":"2024-06-24","cited_by_count":8,"area":"mllm"},{"id":"2502.17943","title":"CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2509.16093","title":"Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses","created":"2025-09-19","cited_by_count":8,"area":null},{"id":"2504.12491","title":"Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?","created":"2025-04-16","cited_by_count":7,"area":null},{"id":"2505.02164","title":"Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair Use","created":"2025-05-04","cited_by_count":6,"area":"rag"},{"id":"2505.12950","title":"GuRE:Generative Query REwriter for Legal Passage Retrieval","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2505.14368","title":"From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2510.01474","title":"AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2407.06798","title":"It Cannot Be Right If It Was Written by AI: On Lawyers' Preferences of Documents Perceived as Authored by an LLM vs a Human","created":"2024-07-09","cited_by_count":5,"area":null},{"id":"2408.07137","title":"ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice","created":"2024-08-13","cited_by_count":5,"area":null},{"id":"2505.12837","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","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":"2411.10137","title":"Legal Evalutions and Challenges of Large Language Models","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2507.16442","title":"Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2404.13885","title":"Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2411.06852","title":"Evaluating Large Language Models on Financial Report Summarization: An Empirical Study","created":"2024-11-11","cited_by_count":3,"area":null},{"id":"2412.12201","title":"Embracing Large Language Models in Traffic Flow Forecasting","created":"2024-12-15","cited_by_count":3,"area":null},{"id":"2502.04379","title":"Can Large Language Models Capture Video Game Engagement?","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2502.12630","title":"Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach","created":"2025-02-18","cited_by_count":3,"area":"agents"},{"id":"2504.10359","title":"DICE: A Framework for Dimensional and Contextual Evaluation of Language Models","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2504.13603","title":"Continual Pre-Training is (not) What You Need in Domain Adaption","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2505.17558","title":"Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection","created":"2025-05-23","cited_by_count":3,"area":"alignment"},{"id":"2506.14387","title":"SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.07748","title":"When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance","created":"2025-07-10","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":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2603.05909","title":"InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.04204","title":"How Does \"English (US)\" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2604.10740","title":"RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game","created":"2026-04-12","cited_by_count":3,"area":"agents"},{"id":"2409.18446","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2412.15902","title":"On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2501.07078","title":"ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2505.15916","title":"BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law","created":"2025-05-21","cited_by_count":2,"area":"rag"},{"id":"2505.19667","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.02946","title":"Abstract Counterfactuals for Language Model Agents","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2506.07853","title":"Modeling the Diachronic Evolution of Legal Norms: An LRMoo-Based, Component-Level, Event-Centric Approach to Legal Knowledge Graphs","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2510.17415","title":"BenCao: An Instruction-Tuned Large Language Model for Traditional Chinese Medicine","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2511.08605","title":"Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2512.19570","title":"The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2603.02588","title":"ExpGuard: LLM Content Moderation in Specialized Domains","created":"2026-03-03","cited_by_count":2,"area":"safety"},{"id":"2606.09389","title":"LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2607.03528","title":"Aligning Language Models with Selective Prediction","created":"2026-07-03","cited_by_count":2,"area":"alignment"},{"id":"2410.12154","title":"Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval","created":"2024-10-16","cited_by_count":1,"area":"lr"},{"id":"2410.20975","title":"Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2411.11289","title":"LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2411.11933","title":"METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2412.20468","title":"A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement","created":"2024-12-29","cited_by_count":1,"area":null},{"id":"2506.00608","title":"PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2507.21419","title":"GovRelBench:A Benchmark for Government Domain Relevance","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2508.09584","title":"SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs","created":"2025-08-13","cited_by_count":1,"area":"mllm"},{"id":"2509.18690","title":"Advances in Large Language Models for Medicine","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2509.20680","title":"Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.21748","title":"Building Domain-Specific Small Language Models via Guided Data Generation","created":"2025-11-23","cited_by_count":1,"area":null},{"id":"2512.11998","title":"Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models","created":"2025-12-12","cited_by_count":1,"area":"alignment"},{"id":"2512.12643","title":"LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.07259","title":"Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.22260","title":"Greater accessibility can amplify discrimination in generative AI","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2603.24518","title":"TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models","created":"2026-03-25","cited_by_count":1,"area":"distill"},{"id":"2604.16270","title":"From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2606.10217","title":"Alignment Defends LLMs from Property Inference Attacks","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2606.15646","title":"NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2410.14353","title":"Assistive AI for Augmenting Human Decision-making","created":"2024-10-18","cited_by_count":0,"area":null}],"next_cursor":"100"}