Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
Paper • 2610.35295 • Published • 4
WeAct Project
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Datasearch
submitted a
paper to Daily Papers 12 days ago
Datasearch
authored 3
papers 12 days ago
WeAct: Dynamic Weight Switching as Agent Actions
Paper • 2610.26847 • Published
SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs
Paper • 2609.10901 • Published
Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
Paper • 2610.35295 • Published • 4
Datasearch
updated a
dataset about 2 months ago
Datasearch
updated a
dataset 6 months ago
Datasearch
published a
dataset 6 months ago
Corning
updated a
dataset 6 months ago
Corning
authored 3
papers about 2 years ago
Themis: Towards Flexible and Interpretable NLG Evaluation
Paper • 2406.18365 • Published
Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation
Paper • 2402.11493 • Published
ALCUNA: Large Language Models Meet New Knowledge
Paper • 2310.14820 • Published • 1