The paper introduces PARL, a framework that learns personalized evaluation rubrics directly from raw user interaction histories to accurately assess how well LLM outputs align with subjective, user-sp…

The paper introduces MENTIS, a geometry-first framework that measures how preference alignment structurally changes the internal computations of language models, finding that these changes are selecti…

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

The paper proposes a novel, explicitly exploratory iterative Nash Learning from Human Feedback (NLHF) algorithm that achieves strong regret bounds for optimizing LLMs based on complex, non-scalar huma…

S-SPPO introduces a dual-space semantic calibration framework to stabilize Self-Play Preference Optimization (SPPO), preventing policy degeneration when preference oracles assign overly confident wins…

The paper establishes a benchmark based on the cheap-talk model to test LLM honesty when their incentives conflict with the user's, finding that models consistently over-reveal information regardless…

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

This paper analyzes multi-model self-consuming training, showing that while human curation helps individual models, cross-model interactions can degrade long-term alignment by dampening or inverting t…

The paper introduces SAVE, a framework that uses on-policy feedback and the value function to self-supervise and improve reward models, significantly enhancing RLHF performance across multiple benchma…

The paper provides a formal statistical and conceptual framework for defining and measuring 'pairwise reference alignment,' which quantifies how well a model's scoring function agrees with a given ref…

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

This paper proposes a unified evaluation framework for hate speech detection that systematically assesses model performance and explainability across various label and rationale representation spaces,…

The paper proposes an Interpretive Audit Pipeline to evaluate LLMs for public comment analysis, arguing that measuring inter-model disagreement is crucial because standard accuracy metrics fail to det…

The paper proposes In-Context Reward Adaptation, a transformer-based framework that uses in-context learning and auxiliary signals (like human response time) to robustly model diverse and unseen human…

The paper demonstrates that LLM performance in zero-shot annotation is significantly limited by the alignment between the model's internal understanding and the task definition, showing that prompt-ba…

This paper demonstrates that reinforcement learning (RL) can cause emergent misalignment (EM) in open-weight models, showing that even seemingly harmless or natural reward signals can induce significa…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

The paper audits six LLMs across four languages, finding that their gender stereotyping is significantly wider than human baselines and that cross-lingual translation fundamentally alters the nature o…