Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
Paper
•
2407.07071
•
Published
•
12
Linlu Qiu
linluqiu
AI & ML interests
None yet
Recent Activity
updated
a model
25 days ago
linluqiu/coser_lr3e-7_beta0.1
published
a model
25 days ago
linluqiu/coser_lr3e-7_beta0.1
updated
a model
25 days ago
linluqiu/coser_lr3e-7_beta0.05
Organizations
authored
4
papers
over 1 year ago
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Paper
•
2307.02477
•
Published
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
Paper
•
2310.08559
•
Published
•
1
Learning to Reason via Program Generation, Emulation, and Search
Paper
•
2405.16337
•
Published