{"total":74,"rows":[{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688,"area":"mllm"},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83,"area":"lr"},{"id":"2406.12718","title":"Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention","created":"2024-06-18","cited_by_count":74,"area":"mllm"},{"id":"2410.01707","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","created":"2024-10-02","cited_by_count":64,"area":"lr"},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2406.02301","title":"mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models","created":"2024-06-04","cited_by_count":33,"area":"lr"},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2312.15918","title":"Supervised Knowledge Makes Large Language Models Better In-context Learners","created":"2023-12-26","cited_by_count":20,"area":null},{"id":"2405.17871","title":"Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment","created":"2024-05-28","cited_by_count":20,"area":"mllm"},{"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":"2406.17519","title":"Entropy-Based Decoding for Retrieval-Augmented Large Language Models","created":"2024-06-25","cited_by_count":19,"area":"rag"},{"id":"2402.14874","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","created":"2024-02-21","cited_by_count":16,"area":"lr"},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2403.19094","title":"Learning From Correctness Without Prompting Makes LLM Efficient Reasoner","created":"2024-03-28","cited_by_count":15,"area":"lr"},{"id":"2402.05467","title":"Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia","created":"2024-02-08","cited_by_count":14,"area":"safety"},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13,"area":null},{"id":"2407.07412","title":"Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2411.15839","title":"VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding","created":"2024-11-24","cited_by_count":12,"area":"mllm"},{"id":"2412.20372","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","created":"2024-12-29","cited_by_count":12,"area":"lr"},{"id":"2502.01662","title":"Fast Large Language Model Collaborative Decoding via Speculation","created":"2025-02-01","cited_by_count":12,"area":null},{"id":"2312.14335","title":"Context-aware Decoding Reduces Hallucination in Query-focused Summarization","created":"2023-12-21","cited_by_count":11,"area":null},{"id":"2503.10602","title":"TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention","created":"2025-03-13","cited_by_count":11,"area":"mllm"},{"id":"2504.00597","title":"On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation","created":"2025-04-01","cited_by_count":10,"area":"rag"},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2408.04023","title":"Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity","created":"2024-08-07","cited_by_count":8,"area":null},{"id":"2410.01556","title":"Integrative Decoding: Improve Factuality via Implicit Self-consistency","created":"2024-10-02","cited_by_count":8,"area":"lr"},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2505.24872","title":"ProxyThinker: Test-Time Guidance through Small Visual Reasoners","created":"2025-05-30","cited_by_count":8,"area":"lr"},{"id":"2602.23306","title":"ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding","created":"2026-02-26","cited_by_count":7,"area":"lr"},{"id":"2502.06282","title":"Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE","created":"2025-02-10","cited_by_count":6,"area":"lr"},{"id":"2602.18232","title":"Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning","created":"2026-02-20","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2507.02226","title":"DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"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":"2507.02128","title":"CROP: Circuit Retrieval and Optimization with Parameter Guidance using LLMs","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2510.07962","title":"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"id":"2602.22144","title":"NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors","created":"2026-02-25","cited_by_count":3,"area":"mllm"},{"id":"2604.10410","title":"CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2607.08690","title":"A Practical Investigation of Training-free Relaxed Speculative Decoding","created":"2026-07-09","cited_by_count":3,"area":"inference"},{"id":"2602.22727","title":"HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2605.12185","title":"Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.25902","title":"Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2407.03600","title":"Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models","created":"2024-07-04","cited_by_count":1,"area":"lr"},{"id":"2410.13077","title":"Tuning Language Models by Mixture-of-Depths Ensemble","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2410.14765","title":"What's New in My Data? Novelty Exploration via Contrastive Generation","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2411.02481","title":"Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning","created":"2024-11-04","cited_by_count":1,"area":"alignment"},{"id":"2509.00869","title":"Exploring and Mitigating Fawning Hallucinations in Large Language Models","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2603.28026","title":"BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA","created":"2026-03-30","cited_by_count":1,"area":"mllm"},{"id":"2606.08850","title":"Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability","created":"2026-06-07","cited_by_count":1,"area":"lr"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2412.17383","title":"Interweaving Memories of a Siamese Large Language Model","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2504.07116","title":"CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning","created":"2025-03-24","cited_by_count":0,"area":"lr"},{"id":"2508.02063","title":"TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs","created":"2025-08-04","cited_by_count":0,"area":"alignment"},{"id":"2512.03803","title":"Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.21744","title":"Temporal Guidance for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.06050","title":"Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering","created":"2026-01-14","cited_by_count":0,"area":"mllm"},{"id":"2604.13538","title":"Synthesizing Instruction-Tuning Datasets with Contrastive Decoding","created":"2026-04-15","cited_by_count":0,"area":"synth"},{"id":"2605.11189","title":"Deep Learning for Protein Complex Prediction and Design","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.29198","title":"Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.01682","title":"Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.12160","title":"A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.05880","title":"Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context","created":"2026-07-07","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":"2608.26213","title":"Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.16646","title":"What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.24196","title":"LoopCD: Loop-wise Contrastive Decoding for Improving Reasoning in Looped Language Models","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.37263","title":"Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.38274","title":"Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02185","title":"Decoding Looped Transformers Better for (Almost) Free","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}