{"total":407,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912,"area":"diffusion"},{"id":"2406.03736","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","created":"2024-06-06","cited_by_count":381,"area":"diffusion"},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2410.18514","title":"Scaling up Masked Diffusion Models on Text","created":"2024-10-24","cited_by_count":199,"area":"diffusion"},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178,"area":null},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"id":"2506.06295","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","created":"2025-05-17","cited_by_count":169,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158,"area":"lr"},{"id":"2403.17806","title":"Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms","created":"2024-03-26","cited_by_count":149,"area":null},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143,"area":null},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119,"area":null},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101,"area":"lr"},{"id":"2311.00059","title":"The Generative AI Paradox: \"What It Can Create, It May Not Understand\"","created":"2023-10-31","cited_by_count":98,"area":null},{"id":"2503.01773","title":"Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas","created":"2025-03-03","cited_by_count":95,"area":"lr"},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2502.03540","title":"Path Planning for Masked Diffusion Model Sampling","created":"2025-02-05","cited_by_count":80,"area":"diffusion"},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79,"area":"safety"},{"id":"2311.08734","title":"Thread of Thought Unraveling Chaotic Contexts","created":"2023-11-15","cited_by_count":72,"area":"lr"},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2406.02061","title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","created":"2024-06-04","cited_by_count":68,"area":"lr"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2312.17080","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","created":"2023-12-28","cited_by_count":57,"area":"lr"},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2402.14865","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","created":"2024-02-21","cited_by_count":54,"area":"agents"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2403.13799","title":"Reverse Training to Nurse the Reversal Curse","created":"2024-03-20","cited_by_count":49,"area":null},{"id":"2407.08733","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","created":"2024-07-11","cited_by_count":48,"area":"lr"},{"id":"2506.10848","title":"Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles","created":"2025-06-12","cited_by_count":45,"area":null},{"id":"2401.07102","title":"Evolving Code with A Large Language Model","created":"2024-01-13","cited_by_count":43,"area":null},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42,"area":"lr"},{"id":"2402.07321","title":"Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs","created":"2024-02-11","cited_by_count":42,"area":null},{"id":"2406.19470","title":"Changing Answer Order Can Decrease MMLU Accuracy","created":"2024-06-27","cited_by_count":42,"area":null},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40,"area":null},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2506.14429","title":"LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs","created":"2025-06-17","cited_by_count":40,"area":"diffusion"},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2508.14148","title":"DPad: Efficient Diffusion Language Models with Suffix Dropout","created":"2025-08-19","cited_by_count":39,"area":"diffusion"},{"id":"2604.07822","title":"Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers","created":"2026-04-09","cited_by_count":37,"area":"lr"},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36,"area":null},{"id":"2405.02079","title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2310.10322","title":"Evaluating the Reversal Curse in Model Editing","created":"2023-10-16","cited_by_count":34,"area":null},{"id":"2311.00237","title":"The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis","created":"2023-11-01","cited_by_count":34,"area":null},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34,"area":null},{"id":"2507.11097","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","created":"2025-07-15","cited_by_count":34,"area":"inference"},{"id":"2406.15720","title":"Scaling Laws for Fact Memorization of Large Language Models","created":"2024-06-22","cited_by_count":33,"area":null},{"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":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2404.01019","title":"Source-Aware Training Enables Knowledge Attribution in Language Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2409.13724","title":"Logically Consistent Language Models via Neuro-Symbolic Integration","created":"2024-09-09","cited_by_count":30,"area":null},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2406.04229","title":"The CLRS-Text Algorithmic Reasoning Language Benchmark","created":"2024-06-06","cited_by_count":28,"area":"lr"},{"id":"2505.18761","title":"How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark","created":"2025-05-24","cited_by_count":28,"area":"lr"},{"id":"2404.04659","title":"Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly","created":"2024-04-06","cited_by_count":27,"area":null},{"id":"2405.04669","title":"Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics","created":"2024-05-07","cited_by_count":27,"area":"lr"},{"id":"2407.12034","title":"Understanding Transformers via N-gram Statistics","created":"2024-06-30","cited_by_count":26,"area":null},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25,"area":null},{"id":"2509.23094","title":"d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching","created":"2025-09-27","cited_by_count":25,"area":"inference"},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24,"area":null},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23,"area":null},{"id":"2408.09773","title":"Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?","created":"2024-08-19","cited_by_count":23,"area":null},{"id":"2601.22311","title":"Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents","created":"2026-01-29","cited_by_count":23,"area":"lr"},{"id":"2311.07468","title":"An Analysis and Mitigation of the Reversal Curse","created":"2023-11-13","cited_by_count":22,"area":null},{"id":"2401.08574","title":"Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2405.14804","title":"Can LLMs Solve longer Math Word Problems Better?","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22,"area":null},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2401.09395","title":"Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions","created":"2024-01-17","cited_by_count":20,"area":"lr"},{"id":"2506.00290","title":"DLM-One: Diffusion Language Models for One-Step Sequence Generation","created":"2025-05-30","cited_by_count":20,"area":"diffusion"},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2405.14225","title":"ReactXT: Understanding Molecular \"Reaction-ship\" via Reaction-Contextualized Molecule-Text Pretraining","created":"2024-05-23","cited_by_count":19,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","cited_by_count":17,"area":"mllm"},{"id":"2408.13654","title":"Symbolic Working Memory Enhances Language Models for Complex Rule Application","created":"2024-08-24","cited_by_count":17,"area":"lr"},{"id":"2312.05253","title":"DiSK: A Diffusion Model for Structured Knowledge","created":"2023-12-08","cited_by_count":16,"area":"diffusion"},{"id":"2401.09074","title":"Code Simulation Challenges for Large Language Models","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2405.15880","title":"HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2412.03235","title":"Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?","created":"2024-12-04","cited_by_count":15,"area":"safety"},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2509.16189","title":"Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences","created":"2025-09-19","cited_by_count":15,"area":null}],"next_cursor":"100"}