Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generationby Tobias Leemann, Periklis Petridis,…
Learning Semantic Structure through First-Order-Logic Translationby Akshay Chaturvedi, Nicholas AsherFirst submitted to arxiv on: 4…
LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with…
Agents’ Room: Narrative Generation through Multi-step Collaborationby Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice…
Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inferenceby Wei Cheng, Tianlu Wang, Yanmin…
Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysisby Hongkang Li, Meng Wang, Songtao…
Efficiently Deploying LLMs with Controlled Riskby Michael J. Zellinger, Matt ThomsonFirst submitted to arxiv on:…
Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Imagesby Qingyuan Liu, Avideh ZakhorFirst…
Automated Red Teaming with GOAT: the Generative Offensive Agent Testerby Maya Pavlova, Erik Brinkman, Krithika…
Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysisby Qunzhong Wang, Xiangguo Sun,…