相关论文: Learning from Imperfect Human Feedback: a Tale fro…

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Typically, RLHF involves the initial step of learning a reward model from human feedback,…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second,…

Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language models by decoupling human preferences regarding helpfulness and harmlessness. Existing…

Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM). However, the effectiveness of this approach can be influenced by adversaries, who may intentionally provide misleading…

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Reinforcement Learning from Human Feedback relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to…

This paper investigates the fusion of absolute (reward) and relative (dueling) feedback in stochastic bandits, where both feedback types are gathered in each decision round. We derive a regret lower bound, demonstrating that an efficient…

We study the linear contextual bandit problem in the presence of adversarial corruption, where the interaction between the player and a possibly infinite decision set is contaminated by an adversary that can corrupt the reward up to a…

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…

Reinforcement learning from human feedback (RLHF) has become an essential step in fine-tuning large language models (LLMs) to align them with human preferences. However, human labelers are selfish and have diverse preferences. They may…

State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement…

We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\zeta\geq0$…

This paper addresses online learning with ``corrupted'' feedback. Our learner is provided with potentially corrupted gradients $\tilde g_t$ instead of the ``true'' gradients $g_t$. We make no assumptions about how the corruptions arise:…

Lipschitz bandit is a variant of stochastic bandits that deals with a continuous arm set defined on a metric space, where the reward function is subject to a Lipschitz constraint. In this paper, we introduce a new problem of Lipschitz…

This paper considers two fundamental sequential decision-making problems: the problem of prediction with expert advice and the multi-armed bandit problem. We focus on stochastic regimes in which an adversary may corrupt losses, and we…

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

We study linear contextual bandits under adversarial corruption and heavy-tailed noise with finite $(1+\epsilon)$-th moments for some $\epsilon \in (0,1]$. Existing work that addresses both adversarial corruption and heavy-tailed noise…

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Online learning to rank sequentially recommends a small list of items to users from a large candidate set and receives the users' click feedback. In many real-world scenarios, users browse the recommended list in order and click the first…

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…