{"list":"other","total":44,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119},{"id":"1903.10992","title":"Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation","created":"2019-03-26","cited_by_count":115},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93},{"id":"2410.11325","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","created":"2024-10-15","cited_by_count":90},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36},{"id":"2009.11729","title":"Interpreting and Boosting Dropout from a Game-Theoretic View","created":"2020-09-24","cited_by_count":34},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27},{"id":"2302.13080","title":"Does a Neural Network Really Encode Symbolic Concepts?","created":"2023-02-25","cited_by_count":27},{"id":"2302.13091","title":"Explaining Generalization Power of a DNN Using Interactive Concepts","created":"2023-02-25","cited_by_count":25},{"id":"2011.03623","title":"Feature Removal Is a Unifying Principle for Model Explanation Methods","created":"2020-11-06","cited_by_count":21},{"id":"2412.08139","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","created":"2024-12-11","cited_by_count":19},{"id":"2208.05642","title":"Self-Knowledge Distillation via Dropout","created":"2022-08-11","cited_by_count":18},{"id":"2401.16318","title":"Defining and Extracting generalizable interaction primitives from DNNs","created":"2024-01-29","cited_by_count":14},{"id":"2407.19198","title":"Towards the Dynamics of a DNN Learning Symbolic Interactions","created":"2024-07-27","cited_by_count":13},{"id":"2304.01083","title":"Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?","created":"2023-04-03","cited_by_count":11},{"id":"2302.13095","title":"Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts","created":"2023-02-25","cited_by_count":9},{"id":"2601.09929","title":"Hallucination Detection and Mitigation in Large Language Models","created":"2026-01-14","cited_by_count":4}],"next_cursor":null}