Papers by Sarkar Snigdha Sarathi Das
GreaterPrompt: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization (2025.acl-demo)
Copied to clipboard
| Challenge: | Recent advances in prompt optimization have introduced diverse techniques that automatically enhance prompts to better align model outputs with user expectations. |
| Approach: | They propose a framework that unifies different methods under a unified, customizable API while delivering highly effective prompts for different tasks. |
| Outcome: | The proposed framework unifies multiple methods under a unified, customizable API while delivering highly effective prompts for different tasks. |
CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Named Entity Recognition only learn class-specific semantic features and intermediate representations from source domains, resulting in suboptimal performance. |
| Approach: | They propose a contrastive learning technique that optimizes the inter-token distribution distance for Few-Shot NER. |
| Outcome: | The proposed technique outperforms existing methods by 3%-13% absolute F1 points while showing consistent performance trends. |
Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Named Entity Recognition, Relation Extraction, Semantic Role Labeling are examples of sequence labeling problems that require finetuning to the target format. |
| Approach: | They propose a dynamic sparse finetuning strategy that selectively focuses on a fraction of parameters, informed by feedback from highly regressing examples. |
| Outcome: | The proposed approach improves performance in low-resource settings and in extreme low-level settings. |
Efficient PRM Training Data Synthesis via Formal Verification (2026.findings-acl)
Copied to clipboard
Ryo Kamoi, Yusen Zhang, Nan Zhang, Sarkar Snigdha Sarathi Das, Ranran Haoran Zhang, Wenpeng Yin, Rui Zhang
| Challenge: | Existing approaches for constructing PRM training data rely on human annotation or sampling-based labeling methods that require repeated LLM calls. |
| Approach: | They propose a framework that synthesizes PRM training data by annotating step-level error labels using formal verification tools such as Z3 and Isabelle. |
| Outcome: | The proposed framework synthesizes PRM training data from formal logic and theorem proving tasks without human annotation or additional LLM calls. |
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs (2024.findings-acl)
Copied to clipboard
Sarkar Snigdha Sarathi Das, Chirag Shah, Mengting Wan, Jennifer Neville, Longqi Yang, Reid Andersen, Georg Buscher, Tara Safavi
| Challenge: | Dialogue state tracking (DST) was based on narrow task-oriented conversations . however, large language models have ushered in more flexible open-domain chat systems . |
| Approach: | They propose a method that combines dialogue segmentation and state tracking within open-domain dialogues to improve long context tracking. |
| Outcome: | The proposed method outperforms the state-of-the-art on open-domain dialogue datasets and publicly available datasets. |