{"total":57,"rows":[{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2502.12054","title":"PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning","created":"2025-02-17","cited_by_count":59,"area":"lr"},{"id":"2604.20006","title":"From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents","created":"2026-04-21","cited_by_count":36,"area":"agents"},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28,"area":"alignment"},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17,"area":"lr"},{"id":"2506.07001","title":"Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text","created":"2025-06-08","cited_by_count":17,"area":null},{"id":"2503.01048","title":"Personalize Your LLM: Fake it then Align it","created":"2025-03-02","cited_by_count":15,"area":"alignment"},{"id":"2503.21720","title":"Collab: Controlled Decoding using Mixture of Agents for LLM Alignment","created":"2025-03-27","cited_by_count":14,"area":"agents"},{"id":"2501.00233","title":"Zero-Shot Strategies for Length-Controllable Summarization","created":"2024-12-31","cited_by_count":10,"area":null},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2602.20708","title":"ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction","created":"2026-02-24","cited_by_count":10,"area":"agents"},{"id":"2503.00723","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","created":"2025-03-02","cited_by_count":9,"area":"mllm"},{"id":"2506.12473","title":"TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2506.17863","title":"LLMs for Customized Marketing Content Generation and Evaluation at Scale","created":"2025-06-22","cited_by_count":9,"area":null},{"id":"2503.01539","title":"Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2508.03098","title":"Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation","created":"2025-08-05","cited_by_count":8,"area":"rag"},{"id":"2506.05967","title":"Preference Learning for AI Alignment: a Causal Perspective","created":"2025-06-06","cited_by_count":6,"area":"alignment"},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2602.15143","title":"Protecting Language Models Against Unauthorized Distillation through Trace Rewriting","created":"2026-02-16","cited_by_count":6,"area":"safety"},{"id":"2412.07334","title":"Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2507.07419","title":"MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2510.02384","title":"Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey","created":"2025-09-30","cited_by_count":5,"area":"safety"},{"id":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2507.09508","title":"A Mixture of Linear Corrections Generates Secure Code","created":"2025-07-13","cited_by_count":4,"area":null},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2508.06374","title":"Evaluating Style-Personalized Text Generation: Challenges and Directions","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2508.08550","title":"Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization","created":"2025-08-12","cited_by_count":3,"area":"alignment"},{"id":"2604.03333","title":"Composer Vector: Style-steering Symbolic Music Generation in a Latent Space","created":"2026-04-03","cited_by_count":3,"area":null},{"id":"2502.13544","title":"From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MARKERGEN","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2510.20498","title":"Robust Preference Alignment via Directional Neighborhood Consensus","created":"2025-10-23","cited_by_count":2,"area":"alignment"},{"id":"2511.10656","title":"Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2512.07627","title":"Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization","created":"2025-12-08","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":"2502.14507","title":"Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2508.04047","title":"LaPA$^2$: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2509.02075","title":"How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2511.13640","title":"Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures","created":"2025-11-17","cited_by_count":1,"area":"synth"},{"id":"2603.03312","title":"Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.07599","title":"StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2604.04708","title":"BiST: A Gold Standard Bangla-English Bilingual Corpus for Sentence Structure and Tense Classification with Inter-Annotator Agreement","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.24178","title":"Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment","created":"2026-04-27","cited_by_count":1,"area":"alignment"},{"id":"2605.27117","title":"Position: AI Safety Requires Effective Controllability","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2511.09488","title":"AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree Search","created":"2025-11-12","cited_by_count":0,"area":"synth"},{"id":"2601.07033","title":"Codified Foreshadowing-Payoff Text Generation","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2603.04974","title":"VRM: Teaching Reward Models to Understand Authentic Human Preferences","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2604.01904","title":"Combating Data Laundering in LLM Training","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.04450","title":"Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.07731","title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2606.21121","title":"Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2608.13622","title":"ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.14797","title":"Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2609.12623","title":"SteerDuplex: Steerable Duplex Speech Dialogue Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.15097","title":"Anchors Enhance Controllability and Reasoning of Diffusion Language Models","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}