English
Related papers

Related papers: A novel repetition normalized adversarial reward f…

200 papers

There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and…

Machine Learning · Computer Science 2013-01-14 Lex Weaver , Nigel Tao

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Computation and Language · Computer Science 2019-05-30 Woon Sang Cho , Pengchuan Zhang , Yizhe Zhang , Xiujun Li , Michel Galley , Chris Brockett , Mengdi Wang , Jianfeng Gao

Reward machines are an established tool for dealing with reinforcement learning problems in which rewards are sparse and depend on complex sequences of actions. However, existing algorithms for learning reward machines assume an overly…

Machine Learning · Computer Science 2025-10-20 Jan Corazza , Ivan Gavran , Daniel Neider

The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…

Computation and Language · Computer Science 2020-05-07 Chenguang Zhu

We investigate mathematically the notion of incoherence: a structural issue with reinforcement learning policies derived by naive goal-conditioning of autoregressive models. We focus on the process of re-training models on their own…

Machine Learning · Computer Science 2026-04-02 Jacek Karwowski , Raymond Douglas

The decoding algorithm is critical for open-ended text generation, transforming latent representations into coherent and meaningful outputs. This paper investigates the self-reinforcement effect in text generation and the effectiveness of a…

Computation and Language · Computer Science 2023-10-24 Wenhong Zhu , Hongkun Hao , Rui Wang

In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs)…

Computation and Language · Computer Science 2024-10-08 Thang Nguyen , Peter Chin , Yu-Wing Tai

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…

Machine Learning · Computer Science 2017-11-28 Peter Henderson , Wei-Di Chang , Pierre-Luc Bacon , David Meger , Joelle Pineau , Doina Precup

Many previous proposals for adversarial training of deep neural nets have included di- rectly modifying the gradient, training on a mix of original and adversarial examples, using contractive penalties, and approximately optimizing…

Machine Learning · Computer Science 2016-08-01 Alexander G. Ororbia , C. Lee Giles , Daniel Kifer

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Computation and Language · Computer Science 2025-05-27 Jinyan Su , Claire Cardie

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility…

Machine Learning · Computer Science 2026-02-04 Haichuan Wang , Tao Lin , Lingkai Kong , Ce Li , Hezi Jiang , Milind Tambe

Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates recent developments…

Computation and Language · Computer Science 2023-07-11 I-Chun Chern , Zhiruo Wang , Sanjan Das , Bhavuk Sharma , Pengfei Liu , Graham Neubig

Recent research studies revealed that neural networks are vulnerable to adversarial attacks. State-of-the-art defensive techniques add various adversarial examples in training to improve models' adversarial robustness. However, these…

Machine Learning · Computer Science 2019-09-13 Chang Song , Zuoguan Wang , Hai Li

Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps. A standard solution to speed up the process is to leverage additional reward signals, shaping it to better…

Computation and Language · Computer Science 2022-10-14 Thomas Carta , Pierre-Yves Oudeyer , Olivier Sigaud , Sylvain Lamprier

Adversarial attacks against language models(LMs) are a significant concern. In particular, adversarial samples exploit the model's sensitivity to small input changes. While these changes appear insignificant on the semantics of the input…

Computation and Language · Computer Science 2024-02-06 Aly M. Kassem , Sherif Saad

Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a different sentiment than desired by the user.…

Computation and Language · Computer Science 2022-11-18 Ximing Lu , Sean Welleck , Jack Hessel , Liwei Jiang , Lianhui Qin , Peter West , Prithviraj Ammanabrolu , Yejin Choi

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…

Computation and Language · Computer Science 2020-04-24 Chen Zhu , Yu Cheng , Zhe Gan , Siqi Sun , Tom Goldstein , Jingjing Liu

Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically…

Computation and Language · Computer Science 2022-10-21 Lei Xu , Alfredo Cuesta-Infante , Laure Berti-Equille , Kalyan Veeramachaneni

It has been demonstrated that very simple attacks can fool highly-sophisticated neural network architectures. In particular, so-called adversarial examples, constructed from perturbations of input data that are small or imperceptible to…

Cryptography and Security · Computer Science 2019-04-09 N. Benjamin Erichson , Zhewei Yao , Michael W. Mahoney

Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead…

Machine Learning · Computer Science 2020-01-03 Abdelrhman Saleh , Natasha Jaques , Asma Ghandeharioun , Judy Hanwen Shen , Rosalind Picard
‹ Prev 1 8 9 10 Next ›