arXiv:2606. 12881v2 Announce Type: replace-cross Abstract: We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique.
arXiv:2508. 11847v4 Announce Type: replace-cross Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems -- variants of a Bradley--Terry model -- to dropping a worst-case very small fraction of preference data.
arXiv:2505. 04260v3 Announce Type: replace-cross Abstract: Personalizing LLM responses typically requires users to articulate their preferences through prompting, which can be burdensome at cold start and difficult to articulate in natural language.
arXiv:2410. 15595v4 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical.
arXiv:2606. 30863v1 Announce Type: new Abstract: Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task is underspecified.
arXiv:2609.38860v1 Announce Type: cross Abstract: Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference lear...
arXiv:2606. 05828v1 Announce Type: new Abstract: As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerged as a novel paradigm.
We’re clarifying how ChatGPT’s behavior is shaped and our plans for improving that behavior, allowing more user customization, and getting more public input into our decision-making in these areas.
The paper surveys how AI copilots—AI-powered assistants for knowledge workers and developers—can personalize their behavior by optimizing user preferences. It reviews how preference signals are collected, modeled at different interaction stages, and refined through feedback loops, and introduces a taxonomy of optimization techniques for pre-, mid-, and post-interaction phases. The study evaluates each technique’s strengths, limitations, and design implications, aiming to unify efforts across AI personalization, human‑AI interaction, and language model adaptation.
arXiv:2606. 02754v1 Announce Type: new Abstract: Personalization is a crucial capability of modern language agents.