相关论文: Language Alignment via Nash-learning and Adaptive …

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing…

Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on human annotations provided by a select cohort of…

Benefiting from the strong reasoning capabilities, Large language models (LLMs) have demonstrated remarkable performance in recommender systems. Various efforts have been made to distill knowledge from LLMs to enhance collaborative models,…

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each…

As Large Language Models (LLMs) are increasingly deployed in decision-critical domains, it becomes essential to ensure that their confidence estimates faithfully correspond to their actual correctness. Existing calibration methods have…

Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most…

Generative AI offers new opportunities for individualized and adaptive learning, e.g., through large language model (LLM)-based feedback systems. While LLMs can produce effective feedback for relatively straightforward conceptual tasks,…

Aligning language models with human preferences is crucial for reducing errors and biases in these models. Alignment techniques, such as reinforcement learning from human feedback (RLHF), are typically cast as optimizing a tradeoff between…

Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences…

Nash equilibria provide a principled framework for modeling interactions in multi-agent decision-making and control. However, many equilibrium-seeking methods implicitly assume that each agent has access to the other agents' objectives and…

This paper examines the long-run behavior of learning with bandit feedback in non-cooperative concave games. The bandit framework accounts for extremely low-information environments where the agents may not even know they are playing a…

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback (RLxF) methods, involving…

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse…

With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…

Recent advancements in Large Language Models (LLMs) have been remarkable, with new models consistently surpassing their predecessors. These advancements are underpinned by extensive research on various training mechanisms. Among these,…

Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy…

Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective…

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…