Papers by Sirat Samyoun
TokenShapley: Token Level Context Attribution with Shapley Value (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. |
| Approach: | They propose a token-level attribution method that combines Shapley value-based data attribution with KNN-based retrieval techniques to improve attribution accuracy. |
| Outcome: | TokenShapley outperforms state-of-the-art methods on four benchmarks . it achieves an 11–23% improvement in accuracy on the benchmarks. |
Attribution-Guided Multi-Object Hallucination and Bias Detection in Vision-Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing methods struggle with multi-object grounding because language priors dominate visual evidence, causing hallucinated or biased objects to produce attention distributions or similarity scores nearly indistinguishable from those of real objects. |
| Approach: | They propose a Shapley value-based attribution framework that uses Kernel SHAP and multi-layer fusion to detect hallucinated and biased objects. |
| Outcome: | Evaluated on ADE and COCO datasets, SHAPLENS improves hallucination detection accuracy by 8–12% and F1 by 10–14% over baselines. |