Papers by Sachin Pawar
QueryShield: A Platform to Mitigate Enterprise Data Leakage in Queries to External LLMs (2025.naacl-industry)
Copied to clipboard
Nitin Ramrakhiyani, Delton Myalil, Sachin Pawar, Manoj Apte, Rajan M A, Divyesh Saglani, Imtiyazuddin Shaik
| Challenge: | Unrestricted access to external Large Language Models (LLMs) based services like ChatGPT and Gemini can lead to data leakages, especially for large enterprises providing products and services that require confidentiality guarantees. |
| Approach: | They propose a platform that enterprises can use to query external Large Language Models without leaking confidential internal and client information. |
| Outcome: | The proposed solution minimizes data leakage while limiting impact to semantics while preserving the accuracy of the model candidates. |
Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for text classification using autoregressive language models are limited . authors propose a novel technique for text classification using autoreregressives . |
| Approach: | They propose a two-step technique for text classification using autoregressive language models . they use a set of perplexity and log-likelihood based numeric features to elicit a text instance . |
| Outcome: | The proposed technique eliminates parameter updates in LMs and does not limit training examples . it is evaluated across 5 datasets and compares with multiple competent baselines . |
Constructing A Dataset of Support and Attack Relations in Legal Arguments in Court Judgements using Linguistic Rules (2022.lrec-1)
Copied to clipboard
| Challenge: | Argumentation mining is a growing area of research with several interesting practical applications. |
| Approach: | They propose three sets of rules based on linguistic knowledge and distant supervision to identify such relations from Indian Supreme Court judgments. |
| Outcome: | The proposed rules are based on linguistic knowledge and distant supervision and use the source of the argument to build a dataset of Support and Attack relations between sentences in a court judgement with reasonable accuracy. |
Extraction of Message Sequence Charts from Software Use-Case Descriptions (N19-2)
Copied to clipboard
Girish Palshikar, Nitin Ramrakhiyani, Sangameshwar Patil, Sachin Pawar, Swapnil Hingmire, Vasudeva Varma, Pushpak Bhattacharyya
| Challenge: | Software Requirement Specification documents provide natural language descriptions of the core functional requirements as a set of use-cases. |
| Approach: | They propose a linguistic knowledge-based approach to extract software requirements from use-cases using a textual representation of the core functional requirements. |
| Outcome: | The proposed method performs better than existing techniques and improves performance. |
Identification of Alias Links among Participants in Narratives (P18-2)
Copied to clipboard
Sangameshwar Patil, Sachin Pawar, Swapnil Hingmire, Girish Palshikar, Vasudeva Varma, Pushpak Bhattacharyya
| Challenge: | Identifying distinct and independent participants in a narrative is crucial for many NLP applications. |
| Approach: | They propose an approach based on linguistic knowledge for identification of aliases mentioned using proper nouns, pronouns or noun phrases with common noun headword. |
| Outcome: | The proposed approach performs better than the state-of-the-art approach on four diverse history narratives of varying complexity. |
Argumentation and Judgement Factors: LLM-based Discovery and Application in Insurance Disputes (2026.eacl-long)
Copied to clipboard
| Challenge: | In this paper, we focus on finding legal factors for a specific case type under consideration . we propose a multi-step approach for discovering a list of AJFs for . a given case type. |
| Approach: | They propose a multi-step approach for discovering a list of AJFs for a given case type . they construct and evaluate the discovered list on two different types of cases . |
| Outcome: | The proposed approach is based on a set of relevant legal documents and a large-scale LLM. |