π Our new explainability method beats LIME for text models
π Across sentiment, toxicity, and syntax tasks:
β’ +34β135% higher fidelity vs LIME
β’ Often surpasses gradient-based methods
β’ Fully model-agnostic
π Paper: arxiv.org/pdf/2601.11746
#XAI #NLPResearch #ExplainableAI #ResponsibleAI #phdlife
#DigitalBehavior #MLResearch #NLPResearch #SocialMediaData
#CallForPapers: Our full-day workshop at The Web Conference 2026 #TheWebConf2026 invites submissions on reproducible and reusable computational approaches for social and #WebData.
π easychair.org/cfp/r2...
Deadline: Dec 18th, 2025
Postdoc position β Kingβs College London, UK
ERC-funded COALA project in #ComputationalLinguistics
Eligibility: PhD
Deadline: 02 December 2025
Details: higherjobz.com/postdoctoral...
#AcademicJobs #UKJobs #PostdocJobs #NLPResearch #DigitalHumanities @kingscollegelondon.bsky.social
π buff.ly/S0DSZzt
β½οΈ Xiangjue Dong (1st author), Cong Wang, Millenium Bismay, and James Caverlee
#NLP #NLPResearch #LLMs #GenAI #AI
π Listen to the full conversation here:
π¬ YouTube: www.youtube.com/watch?v=DPhq...
π Apple Podcasts: podcasts.apple.com/ca/podcast/w...
π§ Spotify: open.spotify.com/episode/7aHP...
π Paper: arxiv.org/pdf/2507.02833
#WomenInAI #AIResearch #LLMs #ReinforcementLearning #NLPResearch (7/7π§΅)