Truncation Sampling as Language Model Desmoothing

27 October 2022

John Hewitt

Christopher D. Manning

Percy Liang

BDL

ArXiv PDF HTML

Papers citing "Truncation Sampling as Language Model Desmoothing"

50 / 58 papers shown

Title
Model Hemorrhage and the Robustness Limits of Large Language Models Ziyang Ma Z. Li L. Zhang Gui-Song Xia Bo Du Liangpei Zhang Dacheng Tao 54 0 0 31 Mar 2025
Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models Tom Kempton Stuart Burrell 32 0 0 27 Mar 2025
Uncertainty-Aware Decoding with Minimum Bayes Risk Nico Daheim Clara Meister Thomas Möllenhoff Iryna Gurevych 53 0 0 07 Mar 2025
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens Tong Wu Junzhe Shen Zixia Jia Y. Wang Zilong Zheng 78 0 0 26 Feb 2025
Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption Alireza Nik Michael A. Riegler P. Halvorsen 33 0 0 17 Feb 2025
Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models Yeming Wen Swarat Chaudhuri 29 0 0 11 Nov 2024
Quasi-random Multi-Sample Inference for Large Language Models Aditya Parashar Aditya Vikram Singh Avinash Amballa Jinlin Lai Benjamin Rozonoyer LRM 56 0 0 09 Nov 2024
Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models Mohammad Beigi Sijia Wang Ying Shen Zihao Lin Adithya Kulkarni ... Ming Jin Jin-Hee Cho Dawei Zhou Chang-Tien Lu Lifu Huang 21 1 0 26 Oct 2024
Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding Hidetaka Kamigaito Hiroyuki Deguchi Yusuke Sakai Katsuhiko Hayashi Taro Watanabe 41 1 0 19 Oct 2024
Hard-Constrained Neural Networks with Universal Approximation Guarantees Youngjae Min Anoopkumar Sonar PINN 12 0 0 14 Oct 2024
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement Yuxi Xie Anirudh Goyal Xiaobao Wu Xunjian Yin Xiao Xu Min-Yen Kan Liangming Pan William Yang Wang LRM 51 1 0 12 Oct 2024
Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling Yuejiang Liu Jubayer Ibn Hamid Annie Xie Yoonho Lee Maximilian Du Chelsea Finn OffRL 51 5 0 30 Aug 2024
Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation Yuxuan Zhou M. Keuper Mario Fritz 23 5 0 24 Aug 2024
Don't Throw Away Data: Better Sequence Knowledge Distillation Jun Wang Eleftheria Briakou Hamid Dadkhahi Rishabh Agarwal Colin Cherry Trevor Cohn 39 5 0 15 Jul 2024
Improving Self Consistency in LLMs through Probabilistic Tokenization Ashutosh Sathe Divyanshu Aggarwal Sunayana Sitaram 37 4 0 04 Jul 2024
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models Sean Welleck Amanda Bertsch Matthew Finlayson Hailey Schoelkopf Alex Xie Graham Neubig Ilia Kulikov Zaid Harchaoui 33 47 0 24 Jun 2024
Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation Boxuan Lyu Hidetaka Kamigaito Kotaro Funakoshi Manabu Okumura 36 0 0 17 Jun 2024
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy Haw-Shiuan Chang Nanyun Peng Mohit Bansal Anil Ramakrishna Tagyoung Chung HILM 33 2 0 11 Jun 2024
Evaluating the World Model Implicit in a Generative Model Keyon Vafa Justin Y. Chen Jon M. Kleinberg S. Mullainathan Ashesh Rambachan 86 26 0 06 Jun 2024
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms Firas Trabelsi David Vilar Mara Finkelstein Markus Freitag 29 6 0 05 Jun 2024
RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors Liam Dugan Alyssa Hwang Filip Trhlik Josh Magnus Ludan Andrew Zhu Hainiu Xu Daphne Ippolito Christopher Callison-Burch DeLMO AAML 33 40 0 13 May 2024
On the True Distribution Approximation of Minimum Bayes-Risk Decoding Atsumoto Ohashi Ukyo Honda Tetsuro Morimura Yuu Jinnai 24 2 0 31 Mar 2024
Recurrent Drafter for Fast Speculative Decoding in Large Language Models Aonan Zhang Chong-Jun Wang Yi Wang Xuanyu Zhang Yunfei Cheng 26 15 0 14 Mar 2024
On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization Lorenzo Jaime Yu Flores Arman Cohan HILM 38 2 0 09 Mar 2024
Improving Open-Ended Text Generation via Adaptive Decoding Wenhong Zhu Hong-ping Hao Zhiwei He Yiming Ai Rui Wang 21 5 0 28 Feb 2024
Linear-time Minimum Bayes Risk Decoding with Reference Aggregation Jannis Vamvas Rico Sennrich 35 15 0 06 Feb 2024
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Tianle Cai Yuhong Li Zhengyang Geng Hongwu Peng Jason D. Lee De-huai Chen Tri Dao 29 246 0 19 Jan 2024
Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation Giorgos Vernikos Andrei Popescu-Belis 30 14 0 12 Jan 2024
Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding Yuu Jinnai Ukyo Honda Tetsuro Morimura Peinan Zhang 26 6 0 10 Jan 2024
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding Yuu Jinnai Kaito Ariu 21 8 0 05 Jan 2024
Applying Large Language Models and Chain-of-Thought for Automatic Scoring Gyeong-Geon Lee Ehsan Latif Xuansheng Wu Ninghao Liu Xiaoming Zhai 31 86 0 30 Nov 2023
Faster Minimum Bayes Risk Decoding with Confidence-based Pruning Julius Cheng Andreas Vlachos 42 21 0 25 Nov 2023
Model-Based Minimum Bayes Risk Decoding for Text Generation Yuu Jinnai Tetsuro Morimura Ukyo Honda Kaito Ariu Kenshi Abe 15 6 0 09 Nov 2023
Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation Wenhong Zhu Hong-ping Hao Rui Wang 34 4 0 23 Oct 2023
Evaluating Large Language Models on Controlled Generation Tasks Jiao Sun Yufei Tian Wangchunshu Zhou Nan Xu Qian Hu Rahul Gupta John Wieting Nanyun Peng Xuezhe Ma LRM ELM 28 60 0 23 Oct 2023
Benchmarking and Improving Text-to-SQL Generation under Ambiguity Adithya Bhaskar Tushar Tomar Ashutosh Sathe Sunita Sarawagi 33 17 0 20 Oct 2023
Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model Christian Tomani David Vilar Markus Freitag Colin Cherry Subhajit Naskar Mara Finkelstein Xavier Garcia Daniel Cremers 18 7 0 10 Oct 2023
Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Models Marco Bronzini Carlo Nicolini Bruno Lepri Andrea Passerini Jacopo Staiano 26 2 0 09 Oct 2023
Closing the Curious Case of Neural Text Degeneration Matthew Finlayson John Hewitt Alexander Koller Swabha Swayamdipta Ashish Sabharwal 24 16 0 02 Oct 2023
It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk Amanda Bertsch Alex Xie Graham Neubig Matthew R. Gormley 33 31 0 02 Oct 2023
MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods M. Finkelstein Subhajit Naskar Mehdi Mirzazadeh Apurva Shah Markus Freitag 45 26 0 19 Sep 2023
Uncertainty in Natural Language Generation: From Theory to Applications Joris Baan Nico Daheim Evgenia Ilia Dennis Ulmer Haau-Sing Li Raquel Fernández Barbara Plank Rico Sennrich Chrysoula Zerva Wilker Aziz UQLM 17 40 0 28 Jul 2023
Extracting Molecular Properties from Natural Language with Multimodal Contrastive Learning Romain Lacombe Andrew Gaut Jeff He D. Lüdeke Kateryna Pistunova 16 2 0 22 Jul 2023
On the Efficacy of Sampling Adapters Clara Meister Tiago Pimentel Luca Malagutti Ethan Gotlieb Wilcox Ryan Cotterell 25 12 0 07 Jul 2023
MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies Shiyue Zhang Shijie Wu Ozan Irsoy Steven Lu Mohit Bansal Mark Dredze David S. Rosenberg 13 9 0 26 May 2023
Look-back Decoding for Open-Ended Text Generation Nan Xu Chunting Zhou Asli Celikyilmaz Xuezhe Ma 13 9 0 22 May 2023
A Frustratingly Simple Decoding Method for Neural Text Generation Haoran Yang Deng Cai Huayang Li Wei Bi Wai Lam Shuming Shi 44 11 0 22 May 2023
Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation Markus Freitag Behrooz Ghorbani Patrick Fernandes 18 40 0 17 May 2023
Conformal Nucleus Sampling Shauli Ravfogel Carlos Wert Carvajal M.F. Eggl UQLM 67 20 0 04 May 2023
Stealing the Decoding Algorithms of Language Models A. Naseh Kalpesh Krishna Mohit Iyyer Amir Houmansadr MLAU 50 20 0 08 Mar 2023