English
Related papers

Related papers: Penalty Decoding: Well Suppress the Self-Reinforce…

200 papers

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental…

Artificial Intelligence · Computer Science 2025-02-05 Ning Dai , Zheng Wu , Renjie Zheng , Ziyun Wei , Wenlei Shi , Xing Jin , Guanlin Liu , Chen Dun , Liang Huang , Lin Yan

Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the next-token in a sequence, with reinforcement learning…

Machine Learning · Computer Science 2025-12-18 Nikolaos Tsilivis , Eran Malach , Karen Ullrich , Julia Kempe

Text editing, such as grammatical error correction, arises naturally from imperfect textual data. Recent works frame text editing as a multi-round sequence tagging task, where operations -- such as insertion and substitution -- are…

Computation and Language · Computer Science 2022-10-25 Ning Shi , Bin Tang , Bo Yuan , Longtao Huang , Yewen Pu , Jie Fu , Zhouhan Lin

Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Chaofeng Chen , Annan Wang , Haoning Wu , Liang Liao , Wenxiu Sun , Qiong Yan , Weisi Lin

Large language models (LLMs) like ChatGPT and GPT-4 have attracted great attention given their surprising performance on a wide range of NLP tasks. Length controlled generation of LLMs emerges as an important topic, which enables users to…

Computation and Language · Computer Science 2023-10-03 Renlong Jie , Xiaojun Meng , Lifeng Shang , Xin Jiang , Qun Liu

Cross-lingual text summarization aims at generating a document summary in one language given input in another language. It is a practically important but under-explored task, primarily due to the dearth of available data. Existing methods…

Computation and Language · Computer Science 2020-06-30 Zi-Yi Dou , Sachin Kumar , Yulia Tsvetkov

We study semantic compression for text where meanings contained in the text are conveyed to a source decoder, e.g., for classification. The main motivator to move to such an approach of recovering the meaning without requiring exact…

Information Theory · Computer Science 2023-09-20 Emrecan Kutay , Aylin Yener

High quality arguments are essential elements for human reasoning and decision-making processes. However, effective argument construction is a challenging task for both human and machines. In this work, we study a novel task on…

Computation and Language · Computer Science 2018-05-28 Xinyu Hua , Lu Wang

Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which…

Computation and Language · Computer Science 2024-06-06 Timon Ziegenbein , Gabriella Skitalinskaya , Alireza Bayat Makou , Henning Wachsmuth

Reinforcement learning has become the dominant paradigm for eliciting reasoning and self-correction capabilities in large language models, but its computational expense motivates exploration of alternatives. Inspired by techniques from…

Artificial Intelligence · Computer Science 2025-12-03 David X. Wu , Shreyas Kapur , Anant Sahai , Stuart Russell

Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for…

Machine Learning · Computer Science 2026-05-21 Erfan Aghadavoodi Jolfaei , Daniel Maninger , Abhinav Anand , Mert Tiftikci , Mira Mezini

Generative patent language models can assist humans to write patent text more effectively. The question is how to measure effectiveness from a human-centric perspective and how to improve effectiveness. In this manuscript, a simplified…

Computation and Language · Computer Science 2023-06-06 Jieh-Sheng Lee

We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying different notions of monotonicity. Specifically, we present two sets of contributions. In the first part of the…

Machine Learning · Computer Science 2022-05-18 Joao Monteiro , Mohamed Osama Ahmed , Hossein Hajimirsadeghi , Greg Mori

We propose a deep learning algorithm for high dimensional optimal stopping problems. Our method is inspired by the penalty method for solving free boundary PDEs. Within our approach, the penalized PDE is approximated using the Deep BSDE…

Mathematical Finance · Quantitative Finance 2026-04-07 Yunfei Peng , Pengyu Wei , Wei Wei

Recent advances in generative models for language have enabled the creation of convincing synthetic text or deepfake text. Prior work has demonstrated the potential for misuse of deepfake text to mislead content consumers. Therefore,…

Cryptography and Security · Computer Science 2022-10-19 Jiameng Pu , Zain Sarwar , Sifat Muhammad Abdullah , Abdullah Rehman , Yoonjin Kim , Parantapa Bhattacharya , Mobin Javed , Bimal Viswanath

This paper studied generating natural languages at particular contexts or situations. We proposed two novel approaches which encode the contexts into a continuous semantic representation and then decode the semantic representation into text…

Computation and Language · Computer Science 2016-12-01 Jian Tang , Yifan Yang , Sam Carton , Ming Zhang , Qiaozhu Mei

Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive…

Computation and Language · Computer Science 2024-06-06 Haozhe Ji , Pei Ke , Hongning Wang , Minlie Huang

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial…

Computation and Language · Computer Science 2022-10-25 Han Guo , Bowen Tan , Zhengzhong Liu , Eric P. Xing , Zhiting Hu

While deep reasoning with long chain-of-thought has dramatically improved large language models in verifiable domains like mathematics, its effectiveness for open-ended tasks such as writing remains unexplored. In this paper, we conduct a…

Computation and Language · Computer Science 2026-04-06 Wanlong Liu , Bo Zhang , Chenliang Li , Shaopeng Lai , Yuning Wu , Xuanyu Lei , Ming Yan

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to…

Computation and Language · Computer Science 2022-03-24 Hanning Gao , Lingfei Wu , Hongyun Zhang , Zhihua Wei , Po Hu , Fangli Xu , Bo Long