{"total":159,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178,"area":null},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"area":"safety"},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"area":null},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57,"area":null},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2403.08002","title":"Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation","created":"2024-03-12","cited_by_count":51,"area":null},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43,"area":"lr"},{"id":"2403.01081","title":"LAB: Large-Scale Alignment for ChatBots","created":"2024-03-02","cited_by_count":39,"area":null},{"id":"2406.17169","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","created":"2024-06-24","cited_by_count":39,"area":"lr"},{"id":"2412.01694","title":"Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation","created":"2024-12-02","cited_by_count":37,"area":"lr"},{"id":"2402.12991","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","created":"2024-02-20","cited_by_count":36,"area":"safety"},{"id":"2402.05138","title":"SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark","created":"2024-02-06","cited_by_count":35,"area":null},{"id":"2410.00379","title":"CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"area":"lr"},{"id":"2410.23743","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","created":"2024-10-31","cited_by_count":29,"area":"lr"},{"id":"2411.19865","title":"Reverse Thinking Makes LLMs Stronger Reasoners","created":"2024-11-29","cited_by_count":29,"area":"lr"},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2404.15846","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","created":"2024-04-24","cited_by_count":27,"area":null},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2403.11671","title":"HDLdebugger: Streamlining HDL debugging with Large Language Models","created":"2024-03-18","cited_by_count":26,"area":null},{"id":"2404.18923","title":"Holmes: A Benchmark to Assess the Linguistic Competence of Language Models","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2412.11142","title":"AD-LLM: Benchmarking Large Language Models for Anomaly Detection","created":"2024-12-15","cited_by_count":26,"area":null},{"id":"2406.11668","title":"\"Not Aligned\" is Not \"Malicious\": Being Careful about Hallucinations of Large Language Models' Jailbreak","created":"2024-06-17","cited_by_count":25,"area":"safety"},{"id":"2410.06215","title":"DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback","created":"2024-10-08","cited_by_count":25,"area":"agents"},{"id":"2501.00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","created":"2024-12-31","cited_by_count":25,"area":"rag"},{"id":"2412.14964","title":"Efficient Knowledge Injection in LLMs via Self-Distillation","created":"2024-12-19","cited_by_count":24,"area":"distill"},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"id":"2401.10695","title":"LangBridge: Multilingual Reasoning Without Multilingual Supervision","created":"2024-01-19","cited_by_count":22,"area":"lr"},{"id":"2412.00161","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","created":"2024-11-29","cited_by_count":22,"area":"lr"},{"id":"2402.11886","title":"The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth","created":"2024-02-19","cited_by_count":20,"area":null},{"id":"2405.01787","title":"Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming","created":"2024-05-03","cited_by_count":20,"area":null},{"id":"2410.02108","title":"ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement","created":"2024-10-03","cited_by_count":18,"area":"lr"},{"id":"2406.06326","title":"Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching","created":"2024-06-10","cited_by_count":17,"area":null},{"id":"2503.10995","title":"TigerLLM - A Family of Bangla Large Language Models","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2402.12219","title":"Reformatted Alignment","created":"2024-02-19","cited_by_count":15,"area":"alignment"},{"id":"2402.10646","title":"AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation","created":"2024-02-16","cited_by_count":14,"area":null},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2410.03663","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","created":"2024-10-04","cited_by_count":14,"area":"lr"},{"id":"2312.11361","title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","created":"2023-12-18","cited_by_count":13,"area":"rag"},{"id":"2402.14856","title":"Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning","created":"2024-02-20","cited_by_count":13,"area":"lr"},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2501.03458","title":"Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generation","created":"2025-01-07","cited_by_count":13,"area":null},{"id":"2402.14270","title":"Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2404.04293","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2408.09304","title":"CyberPal.AI: Empowering LLMs with Expert-Driven Cybersecurity Instructions","created":"2024-08-17","cited_by_count":12,"area":null},{"id":"2410.07109","title":"I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy","created":"2024-10-09","cited_by_count":12,"area":"agents"},{"id":"2411.05059","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2504.05571","title":"Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2406.12442","title":"Abstraction-of-Thought Makes Language Models Better Reasoners","created":"2024-06-18","cited_by_count":11,"area":"lr"},{"id":"2407.00497","title":"LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement","created":"2024-06-29","cited_by_count":11,"area":null},{"id":"2504.15047","title":"RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search","created":"2025-04-21","cited_by_count":11,"area":"safety"},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2506.04463","title":"Aligning Large Language Models with Implicit Preferences from User-Generated Content","created":"2025-06-04","cited_by_count":9,"area":"alignment"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2408.12337","title":"Fine-tuning Smaller Language Models for Question Answering over Financial Documents","created":"2024-08-22","cited_by_count":8,"area":"lr"},{"id":"2410.15107","title":"Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models","created":"2024-10-19","cited_by_count":8,"area":"rag"},{"id":"2504.01241","title":"Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2505.12682","title":"RAFP: Identifying LLM Lineages via Rare-Region Fingerprints","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2404.11129","title":"Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales","created":"2024-04-17","cited_by_count":7,"area":"mllm"},{"id":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2401.07466","title":"Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection","created":"2024-01-15","cited_by_count":6,"area":null},{"id":"2402.16211","title":"HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs","created":"2024-02-25","cited_by_count":6,"area":"alignment"},{"id":"2407.01490","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2502.13723","title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values","created":"2025-02-19","cited_by_count":6,"area":"lr"},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","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":"2402.01821","title":"Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2407.16624","title":"Semantic Change Characterization with LLMs using Rhetorics","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2407.19405","title":"Logic Distillation: Learning from Code Function by Function for Decision-making Tasks","created":"2024-07-28","cited_by_count":5,"area":"lr"},{"id":"2409.06595","title":"GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering","created":"2024-09-10","cited_by_count":5,"area":"rag"},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2503.04332","title":"The Challenge of Identifying the Origin of Black-Box Large Language Models","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2512.21002","title":"Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation","created":"2025-12-24","cited_by_count":5,"area":"lr"},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2402.14453","title":"Do LLMs Implicitly Determine the Suitable Text Difficulty for Users?","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2404.17513","title":"A Comprehensive Evaluation on Event Reasoning of Large Language Models","created":"2024-04-26","cited_by_count":4,"area":"lr"},{"id":"2411.10878","title":"Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis","created":"2024-11-16","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":"2506.22666","title":"VERA: Variational Inference Framework for Jailbreaking Large Language Models","created":"2025-06-27","cited_by_count":4,"area":"safety"},{"id":"2509.21294","title":"UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2510.14113","title":"Toward Cybersecurity-Expert Small Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2406.09891","title":"Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2406.19227","title":"Aligning Teacher with Student Preferences for Tailored Training Data Generation","created":"2024-06-27","cited_by_count":3,"area":"distill"},{"id":"2407.12847","title":"Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2408.04910","title":"Unleashing Artificial Cognition: Integrating Multiple AI Systems","created":"2024-08-09","cited_by_count":3,"area":null},{"id":"2410.16534","title":"SoftSRV: Learn to Generate Targeted Synthetic Data","created":"2024-10-21","cited_by_count":3,"area":"synth"}],"next_cursor":"100"}