REVIEW 5 cited by
Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Current dialogue research primarily studies pairwise (two-party) conversations, and does not address the everyday setting where more than two speakers converse together. In this work, we both collect and evaluate multi-party conversations to study this more general case. We use the LIGHT environment to construct grounded conversations, where each participant has an assigned character to role-play. We thus evaluate the ability of language models to act as one or more characters in such conversations. Models require two skills that pairwise-trained models appear to lack: (1) being able to decide when to talk; (2) producing coherent utterances grounded on multiple characters. We compare models trained on our new dataset to existing pairwise-trained dialogue models, as well as large language models with few-shot prompting. We find that our new dataset, MultiLIGHT, which we will publicly release, can help bring significant improvements in the group setting.
Forward citations
Cited by 5 Pith papers
-
MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Games
Non-invasive per-utterance belief probes in Mafia, auto-scored against engine truth, expose poorly calibrated LLM confidence and 1.5× over-prediction of being suspected.
-
ChatMuse: Supporting In-Person Small-Group Conversation Experience with a Proactive Assistive AI Agent in Mixed Reality
A proactive mixed-reality AI agent that privately suggests speech and nonverbal behavior can help one participant feel more engaged in small-group conversations, according to an 18-person within-subject study.
-
Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
RAR improves role-playing agents by distilling character-grounded reasoning traces and optimizing the reasoning style to fit the dialogue scene.
-
Whom to Respond To? A Transformer-Based Model for Multi-Party Social Robot Interaction
A multi-task transformer with two KL-divergence losses improves a social robot's when-and-whom-to-respond accuracy on a new multi-party HRI dataset.
-
Amplifying Minority Voices: AI-Mediated Devil's Advocate System for Inclusive Group Decision-Making
An LLM-powered devil's advocate that paraphrases minority members' private dissents as its own messages could reduce social pressure and increase opinion diversity in group decisions, but the paper provides no user st...
Discussion (0). Continue with ORCID to comment.