A survey that organizes fairness research in LLM-based recommender systems via a two-dimensional taxonomy of bias mechanisms and fairness targets while linking to other trustworthy AI concerns.
Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions
6 Pith papers cite this work, alongside 202 external citations. Polarity classification is still indexing.
6
Pith papers citing it
202
external citations · external index
representative citing papers
ExPerT infers query-specific user expertise from semantic text and keystroke dynamics via LLM prompting to adapt response generation, cutting inference error 65.7% and raising satisfaction 17.52% in a 40-participant study.
Politeness in prompts boosts average LLM response quality by up to 11% but the benefit is language- and model-dependent, with English favoring courteous tones, Hindi deferential ones, and Spanish assertive ones.
TextBridgeGNN pre-trains a graph recommender across domains and uses text-similarity edges to move ID-based knowledge into a new domain, improving cross-domain, multi-domain, and zero-shot recommendations.
ToolRec improves assistant query suggestions by retrieving relevant system tools and applying dual-level click calibration inside weighted KTO, gaining higher CTR and clicks in an online test.
Virtual simulation supports safe mental health intervention testing via agent-based community modeling and embodied individual training spaces.
citing papers explorer
-
Rethinking Fairness in LLM-Based Recommender Systems: A Survey
A survey that organizes fairness research in LLM-based recommender systems via a two-dimensional taxonomy of bias mechanisms and fairness targets while linking to other trustworthy AI concerns.
-
ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues
ExPerT infers query-specific user expertise from semantic text and keystroke dynamics via LLM prompting to adapt response generation, cutting inference error 65.7% and raising satisfaction 17.52% in a 40-participant study.
-
No Universal Courtesy: A Cross-Linguistic, Multi-Model Study of Politeness Effects on LLMs Using the PLUM Corpus
Politeness in prompts boosts average LLM response quality by up to 11% but the benefit is language- and model-dependent, with English favoring courteous tones, Hindi deferential ones, and Spanish assertive ones.
-
TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
TextBridgeGNN pre-trains a graph recommender across domains and uses text-similarity edges to move ID-based knowledge into a new domain, improving cross-domain, multi-domain, and zero-shot recommendations.
-
ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants
ToolRec improves assistant query suggestions by retrieving relevant system tools and applying dual-level click calibration inside weighted KTO, gaining higher CTR and clicks in an online test.
-
Virtual Simulation for Mental Health
Virtual simulation supports safe mental health intervention testing via agent-based community modeling and embodied individual training spaces.