English
Related papers

Related papers: Universal Adversarial Suffixes for Language Models…

200 papers

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Artificial Intelligence · Computer Science 2025-08-11 Yihao Liu , Shuocheng Li , Lang Cao , Yuhang Xie , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and adapt to environment dynamics, highlighting the need for…

Computation and Language · Computer Science 2026-02-10 Xiao Yu , Baolin Peng , Ruize Xu , Yelong Shen , Pengcheng He , Suman Nath , Nikhil Singh , Jiangfeng Gao , Zhou Yu

We introduce a large language model (LLM) capable of processing speech inputs and show that tuning it further with reinforcement learning on human preference (RLHF) enables it to adapt better to disordered speech than traditional…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Chirag Nagpal , Subhashini Venugopalan , Jimmy Tobin , Marilyn Ladewig , Katherine Heller , Katrin Tomanek

Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe metrics for measuring…

Computation and Language · Computer Science 2021-05-03 Ruibo Liu , Chenyan Jia , Jason Wei , Guangxuan Xu , Lili Wang , Soroush Vosoughi

Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing approaches focus on…

Computation and Language · Computer Science 2020-10-20 Wenjuan Han , Liwen Zhang , Yong Jiang , Kewei Tu

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

Machine Learning · Computer Science 2026-05-22 Srujan P Mule , Aniketh Garikaparthi , Manasi Patwardhan

Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training.…

Computation and Language · Computer Science 2024-10-17 Yanjun Chen , Dawei Zhu , Yirong Sun , Xinghao Chen , Wei Zhang , Xiaoyu Shen

Adversarial training in reinforcement learning (RL) is challenging because perturbations cascade through trajectories and compound over time, making fixed-strength attacks either overly destructive or too conservative. We propose…

Machine Learning · Computer Science 2026-01-30 Lucas Schott , Elies Gherbi , Hatem Hajri , Sylvain Lamprier

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Computation and Language · Computer Science 2025-07-29 Yifu Han , Geo Zhang

Adversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when…

Computation and Language · Computer Science 2021-01-05 Eric Wallace , Shi Feng , Nikhil Kandpal , Matt Gardner , Sameer Singh

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Machine Learning · Computer Science 2020-12-22 Somjit Nath , Richa Verma , Abhik Ray , Harshad Khadilkar

The capabilities of Large Language Models (LLMs) are routinely evaluated by other LLMs trained to predict human preferences. This framework--known as LLM-as-a-judge--is highly scalable and relatively low cost. However, it is also vulnerable…

Computation and Language · Computer Science 2026-02-03 Lisa Alazraki , Tan Yi-Chern , Jon Ander Campos , Maximilian Mozes , Marek Rei , Max Bartolo

Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domains. Despite its empirical success, it remains unclear whether…

Machine Learning · Computer Science 2026-01-27 Mingyuan Fan , Weiguang Han , Daixin Wang , Cen Chen , Zhiqiang Zhang , Jun Zhou

Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits…

Artificial Intelligence · Computer Science 2026-03-04 Siwei Wang , Yifei Shen , Haoran Sun , Shi Feng , Shang-Hua Teng , Li Dong , Yaru Hao , Wei Chen

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation…

Machine Learning · Computer Science 2025-10-06 Anisha Gunjal , Anthony Wang , Elaine Lau , Vaskar Nath , Yunzhong He , Bing Liu , Sean Hendryx

Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing. However, this shaped reward introduces learning biases, which reduces the…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Tszhang Guo , Shiyu Chang , Mo Yu , Kun Bai

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…

Machine Learning · Statistics 2021-11-17 Takeru Miyato , Andrew M. Dai , Ian Goodfellow

The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties. Recent studies found that attaching…

Computation and Language · Computer Science 2024-06-05 Hao Wang , Hao Li , Minlie Huang , Lei Sha

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…

Machine Learning · Computer Science 2025-09-11 Lukas Toral , Teddy Lazebnik

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…

Computation and Language · Computer Science 2022-03-25 Hanjie Chen , Yangfeng Ji