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 proposes a comprehensive benchmark to systematically audit how varying persona prompts and model choices affect the technical quality and social representativeness of scholar recommendations…

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coheren…

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 study found that while contextualizing AI responses reduces their persuasive power, combining this technique with conversational warmth restores persuasiveness, suggesting that user deference to A…

This paper introduces personalized empathy, a capability for LLMs to adapt empathetic strategies based on individual user history, and proposes PereGRM, a reward modeling framework that significantly…

The paper introduces ChildEval, a large-scale benchmark designed to systematically evaluate how well large language models can infer and follow complex, child-specific preferences during long-context…

The paper demonstrates that the order and content of external information (the 'feed') an LLM agent consumes before making a decision can significantly and causally steer its final choice, often overr…

The paper demonstrates that the sequence and composition of external information (the 'feed') an LLM agent consumes can significantly and causally steer its final decisions, often overriding its defau…

The paper proposes SPHERE, a novel framework that uses large language models to create semantic user personas, enabling effective cross-domain recommendation knowledge transfer between completely disj…

The paper proposes a persona-based evaluation framework that replaces monolithic AI benchmarks with structured cognitive profiles to capture diverse human perspectives, while also identifying the chal…

Despite having access to web search, users' reliance on conversational AI for information remains high, driven primarily by pre-existing trust and influenced indirectly by the chatbot's conversational…

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 MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current…

The paper advocates for integrating explicit contextual feedback (like reviews and comments) into LLM-based recommender systems to achieve more personalized, transparent, and semantically aligned reco…

The study found that while AI collaboration is promising, highly competent and proactive AI systems can negatively impact human perceptions of ownership and job meaningfulness, suggesting that design…

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…

This paper introduces 'Visual Inception,' a novel attack that poisons long-term memory in agentic recommender systems using images, and proposes CognitiveGuard, a dual-process defense framework to mit…

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 introduces a novel paradigm where a fine-tuned LLM acts as an ancillary predictor to forecast likely advertisers, significantly improving ad recommendation systems by augmenting candidate ge…