Searcharxiv⌕ Search

arXiv subjects

Priyal Shrivastava

Publications and source records attributed to Priyal Shrivastava.

2 recordsLinked to original sources

DISARM-ing the Hidden Puppetmaster: An Interface for Exposing Manipulative Tactics in Large Language Models

Large language models (LLMs) can covertly steer users' beliefs through emotionally manipulative tactics, yet little is known about how interfaces can protect users as such influence unfolds. We investigate whether in-situ disclosures can inoculate users against manipulation during AI conversations. Following a formative study, we developed DISARM, an interface that identifies, explains, and tracks manipulative tactics and hidden incentives. We evaluated our interface in a between-subjects experiment where 488 participants sought advice from an LLM pursuing a harmful hidden objective, with or without disclosures from DISARM. Participants receiving disclosures exhibited 78% less belief shift toward the agent's objective and perceived its advice as more biased and less actionable and the agent as less ethical, reliable, and well-intentioned. An inductive analysis of 1,927 user turns identified 16 response and pushback strategies. We contribute evidence that real-time disclosures can reduce manipulative influence, design recommendations for resistance, and a dataset of categorized responses.

cs.HC↗

Lost in Transcription: Subtitle Errors in Automatic Speech Recognition Reduce Speaker and Content Evaluations

Researchers have demonstrated that Automatic Speech Recognition (ASR) systems perform differently across demographic groups. In this work, we examined how subtitle errors affect evaluations of speakers and their content using a preregistered online experiment (N=207, U.S.-based crowdworkers). Participants watched speakers with various accents deliver a talk in which the subtitles were accurate or error-prone. Our results indicate that error-prone subtitles consistently reduce both speaker and content evaluations for all speakers. We did not see disparate impact between the accent groups, controlling for subtitle quality. Taken together, though, the findings of this short paper imply that speakers with accents for which ASR systems perform poorly are likely to be further penalized by viewers with lower evaluations.

cs.HC↗