Institution profile

Red Hat

Industry researchnorthamerica · us
Official website
Research library62linked papers
Opportunities0open roles
Selected work

Representative Papers

Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialogue

Jan 13, 2026

This study addresses a critical gap in psychological manipulation detection by extending the task beyond text to the underexplored speech modality. The authors introduce SPEECHMENTALMANIP, the first benchmark for detecting covert manipulative language in speech, constructed by augmenting existing textual datasets with high-fidelity, speaker-consistent multi-speaker synthetic audio. Systematic evaluation combines few-shot audio-language models with human annotation to assess performance. Experimental results reveal that while models achieve high specificity in identifying manipulative utterances in speech, their recall is substantially lower than in the textual domain. Human evaluators also exhibit greater uncertainty, highlighting the inherent ambiguity of manipulative cues in spoken language and fundamental differences in cross-modal perception. These findings underscore the unique challenges posed by speech-based manipulation detection and call for modality-aware approaches.

1 citationsRead paper
Recent publications

Latest Papers

Scaling the Lightning Network with Practical Set Reconciliation

Aug 16, 2026

This study addresses the scalability bottleneck caused by the flooding mechanism in the Lightning Network Gossip protocol by proposing AdaptiveIBLT, a set reconciliation-based alternative to traditional synchronization methods. The protocol incorporates a partial decoding enhancement to enable adaptive and efficient reconciliation of topology and channel information. Evaluations via Core-Lightning simulations and real-world network snapshots demonstrate that this approach reduces Gossip reconciliation time from hours to minutes, significantly improving data synchronization efficiency among large-scale nodes. These results effectively validate the scalability and practical utility of set reconciliation in operational network environments, offering a viable solution to current propagation limitations in decentralized payment networks.

0 citationsRead paper