REVIEW 4 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 4 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.
Discussion (0). Sign in to comment.