Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models
Paper • 2604.21193 • Published • 2
Franck Dernoncourt
Franck-Dernoncourt
AI & ML interests
https://scholar.google.com/citations?user=kz2aIc8AAAAJ&hl=en
Recent Activity
Organizations
upvoted 2
papers 5 days ago
upvoted 2
papers about 1 month ago
upvoted 3
papers about 2 months ago
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Paper • 2603.07392 • Published • 18
Agentic Planning with Reasoning for Image Styling via Offline RL
Paper • 2603.07148 • Published • 3
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper • 2603.03646 • Published • 8
upvoted 3
papers 2 months ago
Blind to the Human Touch: Overlap Bias in LLM-Based Summary Evaluation
Paper • 2602.07673 • Published • 1
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
Paper • 2602.09319 • Published • 1
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling
Paper • 2602.09084 • Published • 30
upvoted 2
papers 3 months ago
upvoted 5
papers 7 months ago
MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
Paper • 2510.08783 • Published • 5
Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs
Paper • 2510.07429 • Published • 4
Knowledge Homophily in Large Language Models
Paper • 2509.23773 • Published • 4
The Photographer Eye: Teaching Multimodal Large Language Models to See and Critique like Photographers
Paper • 2509.18582 • Published • 4
CommonForms: A Large, Diverse Dataset for Form Field Detection
Paper • 2509.16506 • Published • 22
upvoted a paper 8 months ago
upvoted 2
papers 10 months ago