As well as presenting this paper, it was a pleasure getting to talk to so many incredible researchers and learn about recent work in the @nlp4posimpact.bsky.social and online abuse and harms communities.

SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models (MisD workshop)
workshop-proceedings.icwsm.org/abstract.php...

Mapping the Scientific Literature on Misinformation Interventions: A Bibliometric Review (COMPASS workshop)
workshop-proceedings.icwsm.org/abstract.php...
@kingcatherine.bsky.social

Bridging Social Media and Search Engines: Dredge Words and the Detection of Unreliable Domains
ojs.aaai.org/index.php/IC...
@evanup.bsky.social

Check out the full paper here, which is upcoming at the ICWSM MisD workshop (see you in Copenhagen!): arxiv.org/pdf/2502.14908

Thanks to my co-authors! @nikitharao.bsky.social @icwsm.bsky.social

Finetuning helps identify counterfactual samples and prevent hallucinations.