{"list":"other","total":84,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2311.17600","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","created":"2023-11-29","cited_by_count":274},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2401.06775","title":"Large language models in healthcare and medical domain: A review","created":"2023-12-12","cited_by_count":127},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96},{"id":"2501.16615","title":"Sparse Autoencoders Trained on the Same Data Learn Different Features","created":"2025-01-28","cited_by_count":93},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84},{"id":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67},{"id":"2411.19939","title":"VLSBench: Unveiling Visual Leakage in Multimodal Safety","created":"2024-11-29","cited_by_count":63},{"id":"2410.06172","title":"Multimodal Situational Safety","created":"2024-10-08","cited_by_count":58},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48},{"id":"2012.07976","title":"NeurIPS 2020 Competition: Predicting Generalization in Deep Learning","created":"2020-12-14","cited_by_count":41},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36},{"id":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35},{"id":"2405.17888","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","created":"2024-05-28","cited_by_count":32},{"id":"2309.07755","title":"Generative AI Text Classification using Ensemble LLM Approaches","created":"2023-09-14","cited_by_count":29},{"id":"2407.01235","title":"A Fingerprint for Large Language Models","created":"2024-07-01","cited_by_count":28},{"id":"2311.08723","title":"Token Prediction as Implicit Classification to Identify LLM-Generated Text","created":"2023-11-15","cited_by_count":27},{"id":"2106.03314","title":"Measuring Generalization with Optimal Transport","created":"2021-06-07","cited_by_count":25},{"id":"2501.18823","title":"Transcoders Beat Sparse Autoencoders for Interpretability","created":"2025-01-31","cited_by_count":25},{"id":"2309.13391","title":"D-Separation for Causal Self-Explanation","created":"2023-09-23","cited_by_count":21},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20},{"id":"2408.11727","title":"Efficient Detection of Toxic Prompts in Large Language Models","created":"2024-08-21","cited_by_count":13},{"id":"2305.04492","title":"MGR: Multi-generator Based Rationalization","created":"2023-05-08","cited_by_count":12},{"id":"2012.06958","title":"$k$-Variance: A Clustered Notion of Variance","created":"2020-12-13","cited_by_count":11},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11},{"id":"2410.06003","title":"Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization","created":"2024-10-08","cited_by_count":11},{"id":"2404.04281","title":"Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights","created":"2024-04-03","cited_by_count":9},{"id":"2409.13712","title":"Good Idea or Not, Representation of LLM Could Tell","created":"2024-09-07","cited_by_count":6},{"id":"2410.16672","title":"The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models","created":"2024-10-22","cited_by_count":5},{"id":"2409.17169","title":"REAL: Response Embedding-based Alignment for LLMs","created":"2024-09-17","cited_by_count":4}],"next_cursor":null}