Papers by Haeun Jang
MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference (2026.findings-acl)
Copied to clipboard
Jeonghyun Park, Ingeol Baek, Seunghyun Yoon, Haeun Jang, Aparna Garimella, Akriti Jain, Nedim Lipka, Hwanhee Lee
| Challenge: | Existing benchmarks on multi-hop QA focus on single-hop and layered ambiguity, but they focus on ambiguous questions . ambiguities can arise at any stage, complicating the reasoning process . |
| Approach: | They propose a benchmark to evaluate ambiguity in multi-hop question answering . they propose MARCH, which uses 2,209 carefully annotated questions . |
| Outcome: | The proposed framework outperforms existing approaches and significantly outperfies existing frameworks. |
Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety research focuses on implicit social norms or text-only settings, overlooking the complexities of multimodal documents. |
| Approach: | They propose a benchmark to assess the safety of large vision-Language Models (LVLMs) they propose 'Document Policy Preservation Benchmark' to assess document policy compliance. |
| Outcome: | The proposed framework outperforms standard prompting defenses in the evaluation of multimodal documents. |