English
Related papers

Related papers: Are PPO-ed Language Models Hackable?

200 papers

We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The agent must follow a multi-stage Standard Operating Procedure (SOP) and strict guardrails (no…

Computation and Language · Computer Science 2026-04-30 Xia Zeng , Yihan Chen , Luhui Liu , Chao Luo , Ye Chen , Zhuoran Zhuang

Language models are pretrained as passive predictors with no incentive to model the consequences of their own outputs. Post-training changes this: a model producing its own responses can benefit from recognizing that it is on-policy. We…

Machine Learning · Computer Science 2026-05-26 Asvin G. , Jack Lindsey

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Machine Learning · Computer Science 2018-12-27 Chen Tessler , Daniel J. Mankowitz , Shie Mannor

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this…

Computation and Language · Computer Science 2023-06-02 Richard Yuanzhe Pang , Vishakh Padmakumar , Thibault Sellam , Ankur P. Parikh , He He

Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group…

Machine Learning · Computer Science 2026-02-04 Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous…

Machine Learning · Computer Science 2019-02-22 Justin Fu , Anoop Korattikara , Sergey Levine , Sergio Guadarrama

While instruction-tuned models have shown remarkable success in various natural language processing tasks, accurately evaluating their ability to follow instructions remains challenging. Existing benchmarks primarily focus on common…

Computation and Language · Computer Science 2024-04-03 Shiyang Li , Jun Yan , Hai Wang , Zheng Tang , Xiang Ren , Vijay Srinivasan , Hongxia Jin

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial…

Computation and Language · Computer Science 2018-08-27 Yi-Lin Tuan , Jinzhi Zhang , Yujia Li , Hung-yi Lee

Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box"…

Computation and Language · Computer Science 2026-04-14 Miaosen Luo , Zhenhao Yang , Jieshen Long , Jinghu Sun , Yichu Liu , Sijie Mai

Large language models have achieved remarkable capabilities, but aligning their outputs with human values and preferences remains a significant challenge. Existing alignment methods primarily focus on positive examples while overlooking the…

Computation and Language · Computer Science 2024-10-17 Shiqi Qiao , Ning Xv , Biao Liu , Xin Geng

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

For a real-world decision-making problem, the reward function often needs to be engineered or learned. A popular approach is to utilize human feedback to learn a reward function for training. The most straightforward way to do so is to ask…

Machine Learning · Computer Science 2023-10-31 Xiang Ji , Huazheng Wang , Minshuo Chen , Tuo Zhao , Mengdi Wang

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

Computation and Language · Computer Science 2025-03-10 Changyu Chen , Zichen Liu , Chao Du , Tianyu Pang , Qian Liu , Arunesh Sinha , Pradeep Varakantham , Min Lin

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences. Despite the effectiveness of such methods in improving the safety of model…

Computation and Language · Computer Science 2023-09-06 Daniel Scalena , Gabriele Sarti , Malvina Nissim , Elisabetta Fersini

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Machine Learning · Computer Science 2026-03-26 Haoyu Wang , Yuxin Chen , Liang Luo , Buyun Zhang , Ellie Dingqiao Wen , Pan Li

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire…

Computation and Language · Computer Science 2025-04-15 Nikita Sorokin , Ivan Sedykh , Valentin Malykh

Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…

Machine Learning · Computer Science 2025-10-21 Ang Li , Yifei Wang , Zhihang Yuan , Stefanie Jegelka , Yisen Wang

Current emotional text-to-speech (TTS) models predominantly conduct supervised training to learn the conversion from text and desired emotion to its emotional speech, focusing on a single emotion per text-speech pair. These models only…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Xiaoxue Gao , Chen Zhang , Yiming Chen , Huayun Zhang , Nancy F. Chen

Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions. We investigate how to generate policies via RL when reward functions are specified in a symbolic language captured by…

Machine Learning · Computer Science 2022-11-24 Andrew C. Li , Zizhao Chen , Pashootan Vaezipoor , Toryn Q. Klassen , Rodrigo Toro Icarte , Sheila A. McIlraith

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely,…

Computation and Language · Computer Science 2024-07-16 Jérémy Scheurer , Mikita Balesni , Marius Hobbhahn
‹ Prev 1 4 5 6 7 8 10 Next ›