{"total":257,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433,"area":"lr"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"area":"safety"},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232,"area":null},{"id":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218,"area":null},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206,"area":null},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"area":"safety"},{"id":"2403.07183","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","created":"2024-03-11","cited_by_count":164,"area":null},{"id":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118,"area":"safety"},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113,"area":"lr"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2505.23840","title":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","created":"2025-05-28","cited_by_count":104,"area":null},{"id":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101,"area":null},{"id":"2406.05644","title":"How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States","created":"2024-06-09","cited_by_count":98,"area":"alignment"},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2401.08565","title":"Tuning Language Models by Proxy","created":"2024-01-16","cited_by_count":89,"area":null},{"id":"2405.12205","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","created":"2024-05-20","cited_by_count":84,"area":"lr"},{"id":"2401.11206","title":"InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance","created":"2024-01-20","cited_by_count":83,"area":"alignment"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79,"area":"safety"},{"id":"2402.05119","title":"A Closer Look at the Limitations of Instruction Tuning","created":"2024-02-03","cited_by_count":77,"area":null},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2406.01288","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","created":"2024-06-03","cited_by_count":70,"area":"safety"},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2412.00473","title":"Jailbreak Large Vision-Language Models Through Multi-Modal Linkage","created":"2024-11-30","cited_by_count":62,"area":"safety"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60,"area":"alignment"},{"id":"2406.14703","title":"Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics","created":"2024-06-20","cited_by_count":59,"area":null},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51,"area":"lr"},{"id":"2403.17031","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","created":"2024-03-24","cited_by_count":50,"area":"alignment"},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46,"area":"alignment"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2401.17633","title":"Navigating the OverKill in Large Language Models","created":"2024-01-31","cited_by_count":44,"area":null},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"area":"lr"},{"id":"2501.12895","title":"Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback","created":"2025-01-22","cited_by_count":41,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2506.02592","title":"Beyond the Surface: Measuring Self-Preference in LLM Judgments","created":"2025-06-03","cited_by_count":31,"area":null},{"id":"2411.03284","title":"SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents","created":"2024-11-05","cited_by_count":30,"area":"agents"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2405.02501","title":"PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning","created":"2024-05-03","cited_by_count":29,"area":null},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2404.14461","title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs","created":"2024-04-22","cited_by_count":28,"area":"safety"},{"id":"2405.04286","title":"Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore","created":"2024-05-07","cited_by_count":27,"area":null},{"id":"2406.04412","title":"Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment","created":"2024-06-06","cited_by_count":27,"area":"alignment"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2401.06785","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples","created":"2024-01-06","cited_by_count":25,"area":"alignment"},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2410.09300","title":"Nudging: Inference-time Alignment of LLMs via Guided Decoding","created":"2024-10-11","cited_by_count":23,"area":null},{"id":"2412.17034","title":"Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models","created":"2024-12-22","cited_by_count":23,"area":"safety"},{"id":"2312.16132","title":"RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models","created":"2023-12-26","cited_by_count":21,"area":null},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2505.15406","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","created":"2025-05-21","cited_by_count":21,"area":"safety"},{"id":"2410.15633","title":"GATEAU: Selecting Influential Samples for Long Context Alignment","created":"2024-10-21","cited_by_count":20,"area":"alignment"},{"id":"2403.04746","title":"LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error","created":"2024-03-07","cited_by_count":19,"area":"agents"},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19,"area":"alignment"},{"id":"2405.19874","title":"Is In-Context Learning Sufficient for Instruction Following in LLMs?","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2402.01737","title":"Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues","created":"2024-01-29","cited_by_count":18,"area":"agents"},{"id":"2404.01856","title":"Poro 34B and the Blessing of Multilinguality","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2404.18466","title":"HFT: Half Fine-Tuning for Large Language Models","created":"2024-04-29","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2502.10486","title":"VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap","created":"2025-02-14","cited_by_count":17,"area":"mllm"},{"id":"2402.11218","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","created":"2024-02-17","cited_by_count":16,"area":null},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"area":null},{"id":"2405.14488","title":"MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2407.15286","title":"Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis","created":"2024-07-21","cited_by_count":15,"area":null},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2403.14401","title":"Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination","created":"2024-03-21","cited_by_count":14,"area":"mllm"},{"id":"2410.03857","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"area":"alignment"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2409.14254","title":"Instruction Following without Instruction Tuning","created":"2024-09-21","cited_by_count":12,"area":null},{"id":"2410.03717","title":"Revisiting the Superficial Alignment Hypothesis","created":"2024-09-27","cited_by_count":12,"area":"alignment"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2506.15606","title":"LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning","created":"2025-06-18","cited_by_count":12,"area":"safety"},{"id":"2410.06809","title":"Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level","created":"2024-10-09","cited_by_count":11,"area":"safety"},{"id":"2506.09227","title":"SoK: Machine Unlearning for Large Language Models","created":"2025-06-10","cited_by_count":11,"area":"safety"},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"area":null}],"next_cursor":"100"}