Related papers: Beyond Semantic Manipulation: Token-Space Attacks …

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial…

Recent research has shown that neural information retrieval techniques may be susceptible to adversarial attacks. Adversarial attacks seek to manipulate the ranking of documents, with the intention of exposing users to targeted content. In…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained…

Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a…

A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM's output that indicates, for example, how likely it is to align with user preferences…

Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts spent on reinforcement learning from human feedback (RLHF),…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar…

Reinforcement learning from human feedback (RLHF) with reward models has advanced alignment of generative models to human aesthetic and perceptual preferences. However, jointly optimizing multiple rewards often incurs an alignment tax,…

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relies on reward or preference models trained on \emph{fixed…

In reinforcement learning, the discount factor $\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become…

Reinforcement learning from human feedback (RLHF) has become a powerful post-training paradigm for aligning large language models with human preferences. A core challenge in RLHF is constructing accurate reward signals, where the…

Autoregressive decoding algorithms that use only past information often cannot guarantee the best performance. Recently, people discovered that looking-ahead algorithms such as Monte Carlo Tree Search (MCTS) with external reward models…

We investigate how effective an attacker can be when it only learns from its victim's actions, without access to the victim's reward. In this work, we are motivated by the scenario where the attacker wants to behave strategically when the…

State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their adversarial robustness remains critically unexplored. This paper studies the phenomenon whereby…

Autonomous agents in safety-critical applications must continuously adapt to dynamic conditions without compromising performance and reliability. This work introduces TAPA (Training-free Adaptation of Programmatic Agents), a novel framework…

We introduce LLaVA-Reward, an efficient reward model designed to automatically evaluate text-to-image (T2I) generations across multiple perspectives, leveraging pretrained multimodal large language models (MLLMs). Existing MLLM-based…

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…

The widespread adoption of Large Language Model (LLM) in commercial and research settings has intensified the need for robust intellectual property protection. Backdoor-based LLM fingerprinting has emerged as a promising solution for this…