{"total":114,"rows":[{"id":"2406.09961","title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","created":"2024-06-14","cited_by_count":129,"area":"lr"},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58,"area":null},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2405.19358","title":"Robustifying Safety-Aligned Large Language Models through Clean Data Curation","created":"2024-05-24","cited_by_count":44,"area":"alignment"},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2410.06097","title":"Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation","created":"2024-10-08","cited_by_count":26,"area":null},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2505.11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","created":"2025-05-14","cited_by_count":24,"area":"safety"},{"id":"2405.13196","title":"Practical and efficient quantum circuit synthesis and transpiling with Reinforcement Learning","created":"2024-05-21","cited_by_count":22,"area":"deeprl"},{"id":"2406.11683","title":"HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2405.14507","title":"Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast","created":"2024-05-23","cited_by_count":19,"area":"moe"},{"id":"2408.13586","title":"Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation","created":"2024-08-24","cited_by_count":19,"area":null},{"id":"2502.12148","title":"HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation","created":"2025-02-17","cited_by_count":18,"area":"mllm"},{"id":"2411.02433","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","created":"2024-11-01","cited_by_count":16,"area":"moe"},{"id":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2509.24086","title":"Do Repetitions Matter? Strengthening Reliability in LLM Evaluations","created":"2025-09-28","cited_by_count":14,"area":null},{"id":"2605.15864","title":"Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination","created":"2026-05-15","cited_by_count":13,"area":"mllm"},{"id":"2410.20210","title":"Looking Beyond The Top-1: Transformers Determine Top Tokens In Order","created":"2024-10-26","cited_by_count":12,"area":null},{"id":"2412.20372","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","created":"2024-12-29","cited_by_count":12,"area":"lr"},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2407.09722","title":"Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference","created":"2024-07-12","cited_by_count":11,"area":"inference"},{"id":"2505.21472","title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","created":"2025-05-27","cited_by_count":11,"area":"mllm"},{"id":"2402.17532","title":"Retrieval is Accurate Generation","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2411.09661","title":"Adaptive Decoding via Latent Preference Optimization","created":"2024-11-14","cited_by_count":10,"area":"alignment"},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2508.20757","title":"GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation","created":"2025-08-28","cited_by_count":10,"area":null},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2505.20016","title":"TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation","created":"2025-05-26","cited_by_count":9,"area":"agents"},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"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":"2602.06791","title":"Rare Event Analysis of Large Language Models","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2603.03825","title":"From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning","created":"2026-03-04","cited_by_count":8,"area":"lr"},{"id":"2605.19537","title":"The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2410.03968","title":"Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2411.13157","title":"Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding","created":"2024-11-20","cited_by_count":7,"area":"inference"},{"id":"2602.08336","title":"UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2505.15291","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2602.02555","title":"Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2409.16560","title":"Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference","created":"2024-09-25","cited_by_count":5,"area":"inference"},{"id":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2510.05987","title":"Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2510.26697","title":"The End of Manual Decoding: Towards Truly End-to-End Language Models","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2407.19526","title":"Impact of Decoding Methods on Human Alignment of Conversational LLMs","created":"2024-07-28","cited_by_count":4,"area":null},{"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":"2506.17299","title":"Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem","created":"2025-06-17","cited_by_count":4,"area":"safety"},{"id":"2410.02220","title":"Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks","created":"2024-10-03","cited_by_count":3,"area":"safety"},{"id":"2412.07282","title":"HARP: Hesitation-Aware Reframing in Transformer Inference Pass","created":"2024-12-10","cited_by_count":3,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2510.22099","title":"Generalization or Memorization: Dynamic Decoding for Mode Steering","created":"2025-10-25","cited_by_count":3,"area":"mechinterp"},{"id":"2602.05883","title":"A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2608.04333","title":"Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2503.20429","title":"Latent Beam Diffusion Models for Generating Visual Sequences","created":"2025-03-26","cited_by_count":2,"area":"diffusion"},{"id":"2504.21020","title":"Context-Enhanced Contrastive Search for Improved LLM Text Generation","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2506.06832","title":"Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2506.07276","title":"Tokenized Bandit for LLM Decoding and Alignment","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.21934","title":"Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation","created":"2025-07-29","cited_by_count":2,"area":"rag"},{"id":"2602.10699","title":"Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2602.18292","title":"Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2608.29988","title":"AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning","created":"2026-08-30","cited_by_count":2,"area":"lr"},{"id":"2501.12980","title":"Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2502.11723","title":"Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.11183","title":"On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2508.13580","title":"A Comparative Study of Decoding Strategies in Medical Text Generation","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2508.15371","title":"Confidence-Modulated Speculative Decoding for Large Language Models","created":"2025-08-21","cited_by_count":1,"area":"inference"},{"id":"2509.25247","title":"Protocode: Prototype-Driven Interpretability for Code Generation in LLMs","created":"2025-09-27","cited_by_count":1,"area":"mechinterp"},{"id":"2510.20387","title":"Relative-Based Scaling Law for Neural Language Models","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.11502","title":"PAS : Prelim Attention Score for Detecting Object Hallucinations in Large Vision--Language Models","created":"2025-11-14","cited_by_count":1,"area":"mllm"},{"id":"2601.22536","title":"Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.00238","title":"DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking","created":"2026-01-30","cited_by_count":1,"area":"rag"},{"id":"2602.03551","title":"Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.17697","title":"Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2605.22579","title":"Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.00477","title":"Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2607.09172","title":"Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.01460","title":"Conformalized Large Language Models under Configuration Shift","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2406.14051","title":"How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2505.14620","title":"Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUs","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.01367","title":"MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations","created":"2025-06-02","cited_by_count":0,"area":"agents"},{"id":"2507.21568","title":"Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages","created":"2025-07-29","cited_by_count":0,"area":"distill"},{"id":"2508.19614","title":"LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation","created":"2025-08-27","cited_by_count":0,"area":"rag"},{"id":"2510.17388","title":"The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2512.00789","title":"Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2601.23048","title":"From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00066","title":"IntentCoding: Amplifying User Intent in Code Generation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.18428","title":"Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation","created":"2026-03-19","cited_by_count":0,"area":"synth"},{"id":"2604.01924","title":"Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.01644","title":"Toward a Principled Framework for Agent Safety Measurement","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.10202","title":"Task-Aware Calibration: Provably Optimal Decoding in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.13247","title":"EMO: Frustratingly Easy Progressive Training of Extendable MoE","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2606.00592","title":"Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07963","title":"Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs","created":"2026-06-06","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}