{"list":"other","total":66,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"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},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"2410.05295","title":"AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs","created":"2024-10-03","cited_by_count":199},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156},{"id":"2006.12655","title":"Perceptual Adversarial Robustness: Defense Against Unseen Threat Models","created":"2020-06-22","cited_by_count":137},{"id":"2005.02819","title":"Geoopt: Riemannian Optimization in PyTorch","created":"2020-05-06","cited_by_count":114},{"id":"1308.5200","title":"Manopt, a Matlab toolbox for optimization on manifolds","created":"2013-08-23","cited_by_count":113},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111},{"id":"2203.03818","title":"Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon","created":"2022-03-08","cited_by_count":101},{"id":"2402.16914","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","created":"2024-02-25","cited_by_count":101},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100},{"id":"1603.03236","title":"Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation","created":"2016-03-10","cited_by_count":94},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88},{"id":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79},{"id":"2402.16717","title":"CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models","created":"2024-02-26","cited_by_count":76},{"id":"1805.08308","title":"geomstats: a Python Package for Riemannian Geometry in Machine Learning","created":"2018-05-21","cited_by_count":71},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","cited_by_count":57},{"id":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53},{"id":"2402.14872","title":"Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs","created":"2024-02-21","cited_by_count":53},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42},{"id":"2402.11493","title":"Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation","created":"2024-02-18","cited_by_count":38},{"id":"2403.01251","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","created":"2024-03-02","cited_by_count":37},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35},{"id":"2402.16006","title":"ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings","created":"2024-02-25","cited_by_count":32},{"id":"2310.14053","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","created":"2023-10-21","cited_by_count":31},{"id":"2303.15441","title":"Zero-shot Model Diagnosis","created":"2023-03-27","cited_by_count":23},{"id":"2502.01236","title":"Eliciting Language Model Behaviors with Investigator Agents","created":"2025-02-03","cited_by_count":23},{"id":"2402.11398","title":"Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis","created":"2024-02-17","cited_by_count":21},{"id":"2401.17072","title":"SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity","created":"2024-01-30","cited_by_count":19},{"id":"1810.01811","title":"McTorch, a manifold optimization library for deep learning","created":"2018-10-03","cited_by_count":16},{"id":"2311.15551","title":"Instruct2Attack: Language-Guided Semantic Adversarial Attacks","created":"2023-11-27","cited_by_count":16},{"id":"1905.13587","title":"GENO -- GENeric Optimization for Classical Machine Learning","created":"2019-05-31","cited_by_count":12},{"id":"2309.07398","title":"Semantic Adversarial Attacks via Diffusion Models","created":"2023-09-14","cited_by_count":12},{"id":"2309.06541","title":"Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity","created":"2023-09-12","cited_by_count":11},{"id":"2210.00973","title":"NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning","created":"2022-10-03","cited_by_count":7},{"id":"2108.12981","title":"The ensmallen library for flexible numerical optimization","created":"2021-08-30","cited_by_count":6},{"id":"2303.13401","title":"Optimization and Optimizers for Adversarial Robustness","created":"2023-03-23","cited_by_count":6},{"id":"2111.13984","title":"NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning","created":"2021-11-27","cited_by_count":5},{"id":"2502.05223","title":"KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs","created":"2025-02-05","cited_by_count":5}],"next_cursor":null}