{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191},{"id":"2203.16487","title":"Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation","created":"2022-03-30","cited_by_count":171},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121},{"id":"1805.04623","title":"Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context","created":"2018-05-12","cited_by_count":113},{"id":"2306.17806","title":"Stay on topic with Classifier-Free Guidance","created":"2023-06-30","cited_by_count":91},{"id":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79},{"id":"2309.09117","title":"Contrastive Decoding Improves Reasoning in Large Language Models","created":"2023-09-17","cited_by_count":74},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59},{"id":"2502.03461","title":"Do Large Language Model Benchmarks Test Reliability?","created":"2025-02-05","cited_by_count":54},{"id":"2507.11851","title":"Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential","created":"2025-07-16","cited_by_count":47},{"id":"2409.07394","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","created":"2024-09-11","cited_by_count":37},{"id":"2305.01628","title":"The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers","created":"2023-05-02","cited_by_count":29},{"id":"2410.18860","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","created":"2024-10-24","cited_by_count":25},{"id":"2505.20199","title":"Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking","created":"2025-05-26","cited_by_count":21},{"id":"2305.12675","title":"A Frustratingly Simple Decoding Method for Neural Text Generation","created":"2023-05-22","cited_by_count":16},{"id":"2402.14874","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","created":"2024-02-21","cited_by_count":16},{"id":"2505.10518","title":"Multi-Token Prediction Needs Registers","created":"2025-05-15","cited_by_count":16},{"id":"2401.05930","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","created":"2024-01-11","cited_by_count":15},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15},{"id":"2509.18362","title":"FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction","created":"2025-09-16","cited_by_count":13},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10},{"id":"2502.03199","title":"Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models","created":"2025-02-05","cited_by_count":7},{"id":"2503.12908","title":"HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models","created":"2025-03-17","cited_by_count":7},{"id":"2409.05923","title":"$\\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding","created":"2024-09-09","cited_by_count":6},{"id":"2502.05825","title":"Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models","created":"2025-02-09","cited_by_count":4},{"id":"2507.04404","title":"LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers","created":"2025-07-06","cited_by_count":3},{"id":"2507.21086","title":"Multi-Amateur Contrastive Decoding for Text Generation","created":"2025-06-22","cited_by_count":3},{"id":"2508.19228","title":"Predicting the Order of Upcoming Tokens Improves Language Modeling","created":"2025-08-26","cited_by_count":3},{"id":"2509.16598","title":"PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality","created":"2025-09-20","cited_by_count":3},{"id":"2508.02184","title":"Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation","created":"2025-08-04","cited_by_count":2}],"next_cursor":null}