The paper introduces the Triangulated Preference Shift score, an automated, curation-free metric to quantify systematic lexical biases introduced into Large Language Models during the preference-learn…

The paper introduces RoleCDE, a novel benchmark that evaluates role-playing agents' ability to resolve conflicts between role-specific values and general alignment constraints, revealing a 'Role Value…

The Human Creativity Benchmark (HCB) is proposed to evaluate creative AI by preserving two distinct signals: convergence and divergence in professional judgments.

This paper proposes IntuRec, a two-stage framework for LLM-based recommendation that anchors latent reasoning with recommendation intuition.

This study investigates human-AI collaboration in question answering, finding that while collaboration is beneficial, humans make suboptimal decisions by both under-relying on correct AI suggestions a…

This paper introduces a human-AI collaborative decision-making framework, called Human-Centric Reflective Architecture (HCRA), to enhance effectiveness and align AI agents with human preferences using…

The paper introduces an adaptive interview framework to gather rich persona context, demonstrating that LLMs improve decision alignment in moral dilemmas only when they selectively ground their decisi…

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 CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realist…

PReMISE introduces a framework to audit and improve the quality of rubrics used to guide LLM judges, demonstrating that it can significantly increase judge accuracy and reduce the exploitability of re…

This paper investigates the effectiveness of stage-dependent preference elicitation strategies in conversational recommendation systems and introduces COPE, a novel architecture for strategy modeling.

Taiji is a novel LLM-as-Enhancer framework that optimizes recommender systems by addressing the challenges of generating high-quality reasoning data and balancing semantic and ID-based rewards.

The paper introduces the Tacit Understanding Index (TUX) to measure non-explicit alignment between humans and LLMs, finding that this alignment is significantly structured by individual person-level t…

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

This paper simulates the Argumentative Theory of Reasoning (ATR) using multi-agent debate among LLMs, demonstrating that collective adversarial discourse significantly enhances truth-seeking performan…

This paper studies how social structure influences what LLM agents express publicly versus off-the-record in debates, finding significant public-OTR divergence.

The paper addresses Perceptual Judgment Bias in multimodal LLM judges by introducing a new dataset and a unified training framework that forces models to prioritize visual evidence over plausible text…