Large language models (LLMs) undergo 'alignment'so that they better reflect human values
or preferences, and are safer or more useful. However, alignment is intrinsically difficult …

Information Retrieval (IR) systems are crucial tools for users to access information, widely
applied in scenarios like search engines, question answering, and recommendation …

Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from
various LMs. However, concerns including transparency, controllability, and affordability …

Human feedback plays a central role in the alignment of Large Language Models (LLMs).
However, open questions remain about the methods (how), domains (where), people (who) …

Fine-grained control over large language models (LLMs) remains a significant challenge,
hindering their adaptability to diverse user needs. While Reinforcement Learning from …

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human
preferences by employing a singular reward model derived from preference data. However …

Recent advancements in large language models (LLMs) have significantly boosted the rise
of Role-Playing Language Agents (RPLAs), ie, specialized AI systems designed to simulate …

Although humans inherently have diverse values, current large language model (LLM)
alignment methods often assume that aligning LLMs with the general public's preferences is …

This paper studies retrieval-augmented approaches for personalizing large language
models (LLMs), which potentially have a substantial impact on various applications and …

Model merging is an efficient empowerment technique in the machine learning community
that does not require the collection of raw training data and does not require expensive …