Post Hoc Explanations of Language Models Can Improve Language Models Satyapriya Krishna
–Neural Information Processing Systems
Our work makes one of the first attempts at highlighting the potential of post hoc explanations as valuable tools for enhancing the effectiveness of LLMs.
Neural Information Processing Systems
Feb-17-2026, 04:44:21 GMT
- Country:
- Europe > Switzerland
- North America > United States
- California > Orange County
- Irvine (0.04)
- Illinois > Champaign County
- Urbana (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California > Orange County
- Genre:
- Research Report > New Finding (1.00)
- Workflow (1.00)
- Technology: