What does this research mean for the field?

Context-specific conversational fillers in embodied virtual agents not only reduce perceived response time but also significantly improve user perceptions of rapport, likability, and willingness for future interaction compared to generic or no fillers. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To investigate how various conversational filler strategies influence user perception, rapport, and perceived latency during interactions with embodied virtual agents.

August 23, 2026ACM Transactions on Applied Perception

Don’t Just Fill the Silence: Exploring Conversational Filler Strategies in Embodied Virtual Agents

View Full Paper

Ask AI

Bookmark

Authors

YLYikuan LiuPurdue University West Lafayette SGSiqi GuoPurdue University West Lafayette CMChristos MousasPurdue University West Lafayette

Discussion

Member takes

Overview

Within-group study demonstrates that context-specific conversational fillers decrease perceived response delay and enhance rapport in virtual agent interactions, highlighting social cue value.

Key Points

To investigate how various conversational filler strategies influence user perception, rapport, and perceived latency during interactions with embodied virtual agents.
Implemented a large language model-driven conversational system using prompt engineering to maintain continuity between fillers and generated responses.
Conducted a within-group laboratory study (N=24) evaluating four interaction conditions: filler-free baseline, short fillers, general fillers, and context-specific fillers.
All conversational filler conditions significantly improved perceived response time and reduced estimated response duration compared to the filler-free baseline.
Context-specific fillers yielded significantly higher filler quality, rapport, likability, and willingness for future interaction, alongside reduced uncanny valley ratings.
Correlational analyses revealed that higher perceived filler quality and favorable perceived response time were associated with more positive evaluations of the virtual agent.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/6a8aae337677a3411444705b https://doi.org/10.1145/3841187

View Full Paper

Ask AI

Bookmark

August 23, 2026ACM Transactions on Applied Perception

Don’t Just Fill the Silence: Exploring Conversational Filler Strategies in Embodied Virtual Agents

View Full Paper

Ask AI

Bookmark

Authors

YLYikuan LiuPurdue University West Lafayette SGSiqi GuoPurdue University West Lafayette CMChristos MousasPurdue University West Lafayette

Discussion

Member takes

Overview

Within-group study demonstrates that context-specific conversational fillers decrease perceived response delay and enhance rapport in virtual agent interactions, highlighting social cue value.

Key Points

To investigate how various conversational filler strategies influence user perception, rapport, and perceived latency during interactions with embodied virtual agents.
Implemented a large language model-driven conversational system using prompt engineering to maintain continuity between fillers and generated responses.
Conducted a within-group laboratory study (N=24) evaluating four interaction conditions: filler-free baseline, short fillers, general fillers, and context-specific fillers.
All conversational filler conditions significantly improved perceived response time and reduced estimated response duration compared to the filler-free baseline.
Context-specific fillers yielded significantly higher filler quality, rapport, likability, and willingness for future interaction, alongside reduced uncanny valley ratings.
Correlational analyses revealed that higher perceived filler quality and favorable perceived response time were associated with more positive evaluations of the virtual agent.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/6a8aae337677a3411444705b https://doi.org/10.1145/3841187

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark