{"list":"other","total":51,"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"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":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86},{"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":"2403.02325","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","created":"2024-03-04","cited_by_count":64},{"id":"2410.15778","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","created":"2024-10-21","cited_by_count":59},{"id":"2403.02991","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","created":"2024-03-05","cited_by_count":54},{"id":"2203.06877","title":"Rethinking Stability for Attribution-based Explanations","created":"2022-03-14","cited_by_count":52},{"id":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47},{"id":"2412.13817","title":"Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection","created":"2024-12-18","cited_by_count":46},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38},{"id":"2405.18330","title":"Frustratingly Easy Test-Time Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":36},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34},{"id":"2411.15268","title":"ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models","created":"2024-11-22","cited_by_count":30},{"id":"2305.10010","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","created":"2023-05-17","cited_by_count":26},{"id":"2409.10053","title":"Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective","created":"2024-09-16","cited_by_count":23},{"id":"2501.13652","title":"LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models","created":"2025-01-23","cited_by_count":23},{"id":"2503.09248","title":"Bayesian Test-Time Adaptation for Vision-Language Models","created":"2025-03-12","cited_by_count":22},{"id":"2505.11080","title":"BLEUBERI: BLEU is a surprisingly effective reward for instruction following","created":"2025-05-16","cited_by_count":17},{"id":"2408.09916","title":"Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit","created":"2024-08-19","cited_by_count":14},{"id":"2403.18680","title":"Non-Linear Inference Time Intervention: Improving LLM Truthfulness","created":"2024-03-27","cited_by_count":9},{"id":"2405.20404","title":"JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution","created":"2024-05-30","cited_by_count":6}],"next_cursor":null}