ConSearcher generates query-based member personas in an LLM conversational tool, yielding higher information-seeking outcomes and engagement than baselines in a 27-person study, with noted risks of over-personalization.
arXiv:2601.15793 [cs.CL] https://arxiv.org/abs/2601.15793
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
CoAct synergistically merges self-rewarding and active learning via self-consistency to select reliable AI labels and oracle-needed samples, delivering 8-13% gains on GSM8K, MATH, and WebInstruct.
GroupGPT decouples intervention timing from response generation via edge-cloud collaboration for multi-user chats, scoring 4.72/5 on the new MUIR benchmark of 2500 segments while cutting token use by up to 3x and adding privacy sanitization.
citing papers explorer
-
ConSearcher: Supporting Conversational Information Seeking in Online Communities with Member Personas
ConSearcher generates query-based member personas in an LLM conversational tool, yielding higher information-seeking outcomes and engagement than baselines in a 27-person study, with noted risks of over-personalization.
-
CoAct: Co-Active LLM Preference Learning with Human-AI Synergy
CoAct synergistically merges self-rewarding and active learning via self-consistency to select reliable AI labels and oracle-needed samples, delivering 8-13% gains on GSM8K, MATH, and WebInstruct.
-
GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
GroupGPT decouples intervention timing from response generation via edge-cloud collaboration for multi-user chats, scoring 4.72/5 on the new MUIR benchmark of 2500 segments while cutting token use by up to 3x and adding privacy sanitization.