The Trustworthy AI Workshop

Accepted Papers

• Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study
  CHAMAS, RABIH*; Khalfaoui Hassani, Ismail; Masquelier, Timothée

• Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate
  Kim, Kyungha; Lee, Sangyun; Huang, Kung-Hsiang*; Chan, Hou Pong; Li, Manling; Ji, Heng

• A Framework for Agents Guiding Foundation Models through Knowledge and Reasoning
  Bhattacharjya, Debarun*; Lee, Junkyu; Agravante, Don Joven; Ganesan, Balaji; Marinescu, Radu

• On the Consistency of Fairness Measurement Methods for Regression Tasks
  Almajed, Abdalwahab*; Tabar, Maryam; Najafirad, Peyman

• A View on Out-of-Distribution Identification from a Statistical Testing Theory Perspective
  Caron, Alberto*; Mavroudis, Vasilios; Hicks, Chris

• Measuring Fairness in Large-Scale Recommendation Systems with Missing Labels
  Jin, Kun*; Dong, Yulong; Hu, Xinghai; Liu, Yang

• MultiFact: A Comprehensive Multimodal Fact-checking Benchmark for Misinformation Detection
  Xie, Anbin*; Zhu, Fuqing; Han, Jizhong; Hu, Songlin

• Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering
  Lee, Yanggyu*; Kim, Jihie

• Combatting Disinformation involving AI-Generated Images through Frequency-guided Channel and Spatial Attention
  Lee, Jiahe Steven; Hsu, Wynne; Lee, Mong Li*

• WWW: Where, Which and Whatever Enhancing Interpretability in Multimodal Deepfake Detection
  Jung, Juho⁺; Lee, Sangyoun⁺; Kang, Jooeon⁺; Na, Yunjin⁺
  ⁺equal contribution

• XAudit : A Theoretical Look at Auditing with Explanations
  Yadav, Chhavi*; Moshkovitz, Michal; Chaudhuri, Kamalika

• Detoxifying Large Language Models via Knowledge Editing
  wang, mengru*; Zhang, Ningyu; Yao, Yunzhi

• Leveraging Gradient Noise for Detection and Filtering of Byzantine Clients
  Errami, Latifa*; Bergou, El houcine; KUNGURTSEV, VYACHESLAV

• First Step for Theoretical and Practical Foundations of Robust Visual Prompting
  Seo, Gyeongdeok⁺; Oh, Changdae⁺; Song, Kyungwoo*
  ⁺equal contribution