Papers by Shreyas N. Samaga
HalluZig: Hallucination Detection using Zigzag Persistence (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection rely on surface-level signals from the model output, overlooking the failures within the model’s internal reasoning process. |
| Approach: | They propose a framework that analyzes the dynamic topology of the evolution of model’s layer-wise attention and leverage zigzag persistence to extract a topological signature. |
| Outcome: | The proposed framework outperforms baselines on multiple benchmarks and is generalizable across models. |