Papers by Dhananjay Ashok
A Representation Sharpening Framework for Zero Shot Dense Retrieval (2026.eacl-long)
Copied to clipboard
| Challenge: | Zero-shot dense retrieval requires generic, pretrained DRs, which struggle to represent semantic differences between similar documents. |
| Approach: | They propose a training-free representation sharpening framework that augments a document’s representation with information that helps differentiate it from similar documents in the corpus. |
| Outcome: | The proposed framework is compatible with prior approaches to zero-shot dense retrieval and consistently improves their performance. |
A Little Human Data Goes A Long Way (2025.acl-short)
Copied to clipboard
| Challenge: | Existing methods to replace human annotation are expensive and limited. |
| Approach: | They investigate the use of synthetic data in Fact Verification and Evidence-based Question Answering by replacing human-generated data with synthetic points on eight diverse datasets. |
| Outcome: | The proposed method shows promise but performance declines when replacing up to 90% of training data with synthetic data are severe . the proposed method can be used to improve models trained on purely synthetic data by including as few as 125 human-generated data points. |
Can VLMs Recall Factual Associations From Visual References? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a systematic deficiency in the multimodal grounding of Vision Language Models is identified . VLMs can recall factual associations when provided a textual reference to an entity . |
| Approach: | They identify a systematic deficiency in the multimodal grounding of Vision Language Models . they show that VLMs struggle to link their internal knowledge of an entity with its image representation . |
| Outcome: | The study shows that VLMs struggle to link internal knowledge with image representations . the findings provide recommendations for future research . |
The student becomes the master: Outperforming GPT3 on Scientific Factual Error Correction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Factual Claim Correction rely on a verification model to guide the correction process. |
| Approach: | They propose a claim correction system that does not require a verifier but outperforms existing methods by a considerable margin. |
| Outcome: | The proposed system outperforms existing methods by a considerable margin on the SciFact dataset, 77% on SciFACT-Open and 72.75% on the CovidFact data set. |