Related papers: SLiC-HF: Sequence Likelihood Calibration with Huma…
Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may…
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…
Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…
Reinforcement Learning from Human Feedback (RLHF) aims to align language models (LMs) with human values by training reward models (RMs) on binary preferences and using these RMs to fine-tune the base LMs. Despite its importance, the…
A growing trend involves integrating human knowledge into learning frameworks, leveraging subtle human feedback to refine AI models. While these approaches have shown promising results in practice, the theoretical understanding of when and…
Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI…
Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works…
Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…
A common and effective strategy for humans to improve an unsatisfactory outcome in daily life is to find a cause of this outcome and correct the cause. In this paper, we investigate whether this human improvement strategy can be applied to…
Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models (LLMs). Traditionally, this method depends on selecting…
In this article, we investigate the alignment of Large Language Models according to human preferences. We discuss the features of training a Preference Model, which simulates human preferences, and the methods and details we found essential…
Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning…
In Reinforcement Learning from Human Feedback (RLHF), it is crucial to learn suitable reward models from human feedback to align large language models (LLMs) with human intentions. However, human feedback can often be noisy, inconsistent,…
Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore…
The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully collecting and tailoring bespoke preference data to each downstream application. However,…
As everyday use cases of large language model (LLM) AI assistants have expanded, it is becoming increasingly important to personalize responses to align to different users' preferences and goals. While reinforcement learning from human…
ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning from human feedback (RLHF) system -- designed to enhance…
Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assuming, implicitly or explicitly, a model of human preferences. A preference model that poorly…
While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. In this work, we study Reinforcement…
We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…