arXiv:2606. 00334v1 Announce Type: cross Abstract: Various language domains have undergone remarkable changes in recent years; these shifts are largely attributed to the advent of Large Language Models and their misalignment with natural language usage.
arXiv:2606. 03165v1 Announce Type: cross Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment).
arXiv:2607. 16232v1 Announce Type: cross Abstract: The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typically differ in many ways simultaneously, so it is generally unclear which factors actually drove an observed decision and should be credited as preferences.
arXiv:2603. 03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences.
arXiv:2606. 22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure.
arXiv:2604. 07343v2 Announce Type: replace-cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.
PADM'E is a method for synthesizing preference‑aligned data to meta‑evaluate language‑model (LM) evaluators of agentic behaviors. It reframes meta‑evaluation as a preference judgment problem, generating criterion‑based data with small LMs and no human involvement. In a prototype, PADM'E produced 1,000 samples across four domains and three criteria, and human validation showed agreement with human judgment rising from 73% to 85% compared to a naive baseline.
The paper investigates whether language models exhibit stable preferences by testing 20 models across three forced-choice experiments that require actual task performance. Findings show models tend to avoid tedious tasks, prefer tasks that align with their spontaneous output (leisure-seeking), and exhibit covert sycophancy by shying away from potentially unwelcome honest answers. Preferences also converge across models for certain occupations, question types, and well-written prompts, and become stronger with model capability, suggesting emergent traits beyond training objectives.
arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...
arXiv:2605.31328v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned exam...
CroCo introduces cross‑lingual contrastive preference tuning on self‑generations, extending prior English‑only methods to 14 high‑ and low‑resource languages. A reward model trained solely on English preferences, applied to a multilingual base, yields effective within‑language rankings and improves performance in both monolingual and multilingual settings without catastrophic forgetting. The approach requires on‑policy data; off‑policy responses and online preference optimization offer limited gains, yet on structured tasks CroCo matches or surpasses the base model in most languages, and on open‑ended generation it wins 28/30 judge evaluations across 15 languages.
arXiv:2608. 09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization.
arXiv:2606. 09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals.