Payel Santra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Payel Santra has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Partha Basuchowdhuri
Indian Association for the Cultivation of Science
9 shared publications - Debasis Ganguly
University of Glasgow, Glasgow, United Kingdom
6 shared publications - Madhusudan Ghosh
Indian Association for the Cultivation of Science, Kolkata, India
5 shared publications - Sudip Kumar Naskar
Jadavpur University, Kolkata, India
3 shared publications Debasis Ganguly
2 shared publications- Shrimon Mukherjee
School of Mathematical and Computational Sciences, Indian Association for the Cultivation of Science, India
2 shared publications
Latest Publications
- 25 March 2026
- Published by Springer Nature
- p. 155-171
Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework
- 25 March 2026
- Published by Springer Nature
- p. 155-171
Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework
- 25 March 2026
- Published by Springer Nature
- p. 518-526
Beyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
- 25 March 2026
- Published by Springer Nature
- p. 518-526
Beyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
- Open Access
Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework
The traditional use-case of query performance prediction (QPP) is to identify which queries perform well and which perform poorly for a given ranking model. A more fine-grained and arguably more challenging extension of this task is to determine which ranking models are most effective for a given query. In this work, we generalize the QPP task and its evaluation into three settings: (i) SingleRanker MultiQuery (SRMQ-PP), corresponding to the standard use case; (ii) MultiRanker SingleQuery (MRSQ-PP), which evaluates a QPP model's ability to select the most effective ranker for a query; and (iii) MultiRanker MultiQuery (MRMQ-PP), which considers predictions jointly across all query ranker pairs. Our results show that (a) the relative effectiveness of QPP models varies substantially across tasks (SRMQ-PP vs. MRSQ-PP), and (b) predicting the best ranker for a query is considerably more difficult than predicting the relative difficulty of queries for a given ranker.
Open AccessBreaking Flat: A Generalised Query Performance Prediction Evaluation Framework
The traditional use-case of query performance prediction (QPP) is to identify which queries perform well and which perform poorly for a given ranking model. A more fine-grained and arguably more challenging extension of this task is to determine which ranking models are most effective for a given query. In this work, we generalize the QPP task and its evaluation into three settings: (i) SingleRanker MultiQuery (SRMQ-PP), corresponding to the standard use case; (ii) MultiRanker SingleQuery (MRSQ-PP), which evaluates a QPP model's ability to select the most effective ranker for a query; and (iii) MultiRanker MultiQuery (MRMQ-PP), which considers predictions jointly across all query ranker pairs. Our results show that (a) the relative effectiveness of QPP models varies substantially across tasks (SRMQ-PP vs. MRSQ-PP), and (b) predicting the best ranker for a query is considerably more difficult than predicting the relative difficulty of queries for a given ranker.
- Open Access
Beyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
The standard practice of query performance prediction (QPP) evaluation is to measure a set-level correlation between the estimated retrieval qualities and the true ones. However, neither this correlation-based evaluation measure quantifies QPP effectiveness at the level of individual queries, nor does this connect to a downstream application, meaning that QPP methods yielding high correlation values may not find a practical application in query-specific decisions in an IR pipeline. In this paper, we propose a downstream-focussed evaluation framework where a distribution of QPP estimates across a list of top-documents retrieved with several rankers is used as priors for IR fusion. While on the one hand, a distribution of these estimates closely matching that of the true retrieval qualities indicates the quality of the predictor, their usage as priors on the other hand indicates a predictor's ability to make informed choices in an IR pipeline. Our experiments firstly establish the importance of QPP estimates in weighted IR fusion, yielding substantial improvements of over 4.5% over unweighted CombSUM and RRF fusion strategies, and secondly, reveal new insights that the downstream effectiveness of QPP does not correlate well with the standard correlation-based QPP evaluation.
Open AccessBeyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
The standard practice of query performance prediction (QPP) evaluation is to measure a set-level correlation between the estimated retrieval qualities and the true ones. However, neither this correlation-based evaluation measure quantifies QPP effectiveness at the level of individual queries, nor does this connect to a downstream application, meaning that QPP methods yielding high correlation values may not find a practical application in query-specific decisions in an IR pipeline. In this paper, we propose a downstream-focussed evaluation framework where a distribution of QPP estimates across a list of top-documents retrieved with several rankers is used as priors for IR fusion. While on the one hand, a distribution of these estimates closely matching that of the true retrieval qualities indicates the quality of the predictor, their usage as priors on the other hand indicates a predictor's ability to make informed choices in an IR pipeline. Our experiments firstly establish the importance of QPP estimates in weighted IR fusion, yielding substantial improvements of over 4.5% over unweighted CombSUM and RRF fusion strategies, and secondly, reveal new insights that the downstream effectiveness of QPP does not correlate well with the standard correlation-based QPP evaluation.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5202-5207
HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5202-5207
Open AccessHF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
- Open Access
- 29 May 2025
- Published by Wiley in WIREs Data Mining and Knowledge Discovery
- Vol. 15 (2)
The “Curious Case of Contexts” in Retrieval‐Augmented Generation With a Combination of Labeled and Unlabeled Data
With the growing reliance on LLMs for a wide range of NLP tasks, optimizing the use of labeled and unlabeled data for effective context generation has become critical. This work explores the interplay between two prominent methodologies in few‐shot learning: in‐context learning (ICL), which utilizes labeled task‐specific data, and retrieval‐augmented generation (RAG), which leverages unlabeled external knowledge to augment generative models. Since each has its individual limitations, we propose a novel hybrid approach to obtain “the best of both worlds” by dynamically integrating both labeled and unlabeled data towards improving the downstream performance of LLMs. Our methodology, which we call LU‐RAG (labeled and unlabeled RAG), recomputes the scores of top‐k labeled instances and top‐m unlabeled passages to refine context selection. Our experimental results demonstrate that LU‐RAG consistently outperforms both standalone ICL and RAG across multiple benchmarks, showing significant gains in downstream performance. Furthermore, we show that LU‐RAG performs better with a semantic neighborhood as compared to a lexical one, highlighting its ability to generalize effectively.
- 29 May 2025
- Published by Wiley in WIREs Data Mining and Knowledge Discovery
- Vol. 15 (2)
Open AccessThe “Curious Case of Contexts” in Retrieval‐Augmented Generation With a Combination of Labeled and Unlabeled Data
With the growing reliance on LLMs for a wide range of NLP tasks, optimizing the use of labeled and unlabeled data for effective context generation has become critical. This work explores the interplay between two prominent methodologies in few‐shot learning: in‐context learning (ICL), which utilizes labeled task‐specific data, and retrieval‐augmented generation (RAG), which leverages unlabeled external knowledge to augment generative models. Since each has its individual limitations, we propose a novel hybrid approach to obtain “the best of both worlds” by dynamically integrating both labeled and unlabeled data towards improving the downstream performance of LLMs. Our methodology, which we call LU‐RAG (labeled and unlabeled RAG), recomputes the scores of top‐k labeled instances and top‐m unlabeled passages to refine context selection. Our experimental results demonstrate that LU‐RAG consistently outperforms both standalone ICL and RAG across multiple benchmarks, showing significant gains in downstream performance. Furthermore, we show that LU‐RAG performs better with a semantic neighborhood as compared to a lexical one, highlighting its ability to generalize effectively.
- 18 August 2024
- Published by Springer Nature
- p. 381-387
“The Absence of Evidence is Not the Evidence of Absence”: Fact Verification via Information Retrieval-Based In-Context Learning
- 18 August 2024
- Published by Springer Nature
- p. 381-387
“The Absence of Evidence is Not the Evidence of Absence”: Fact Verification via Information Retrieval-Based In-Context Learning
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 3073
Leveraging LLMs for Detecting and Modeling the Propagation of Misinformation in Social Networks
Recent success in language generation capabilities of large language models (LLMs), such as GPT, Llama, etc., can potentially lead to concern about their possible misuse in inducing mass agitation and communal hatred via generating fake news and spreading misinformation. Traditional means of developing a misinformation ground-truth dataset do not scale well because of the extensive manual effort required to annotate the data. It is crucial to anticipate and counteract potential adversarial fake information to mitigate detrimental effects and promote societal harmony. To this end, this PhD proposal spans three main research directions. The first concerns investigating ways of developing unsupervised models for fake news identification leveraging retrieval augmented generation (RAG) approaches. In our second thread of work, we explore ways of creating synthetic datasets to eventually train supervised or few-shot example-based models. Another direction of research work involves tracking the propagation of fake information through social networks to develop preventive measures against it.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 3073
Open AccessLeveraging LLMs for Detecting and Modeling the Propagation of Misinformation in Social Networks
Recent success in language generation capabilities of large language models (LLMs), such as GPT, Llama, etc., can potentially lead to concern about their possible misuse in inducing mass agitation and communal hatred via generating fake news and spreading misinformation. Traditional means of developing a misinformation ground-truth dataset do not scale well because of the extensive manual effort required to annotate the data. It is crucial to anticipate and counteract potential adversarial fake information to mitigate detrimental effects and promote societal harmony. To this end, this PhD proposal spans three main research directions. The first concerns investigating ways of developing unsupervised models for fake news identification leveraging retrieval augmented generation (RAG) approaches. In our second thread of work, we explore ways of creating synthetic datasets to eventually train supervised or few-shot example-based models. Another direction of research work involves tracking the propagation of fake information through social networks to develop preventive measures against it.
- Open Access
- 4 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 227-231
BLINKtextsubscriptLSTM: BioLinkBERT and LSTM based approach for extraction of PICO frame from Clinical Trial Text
- 4 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 227-231
Open AccessBLINKtextsubscriptLSTM: BioLinkBERT and LSTM based approach for extraction of PICO frame from Clinical Trial Text
- Open Access
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 149-152
Unleashing the Power of Large Language Models: A Hands-On Tutorial
LLMs have opened up possibilities for advancing the state-of-the-art in natural language processing (NLP). In this tutorial, we present the audience with an introduction to LLMs and the associated challenges. The tutorial is structured in the following manner. First, we provide a brief preface that outlines the fundamental principles of NLP, following which, we explore the area of distributional representation learning for NLP. Then, we delve into the essential component of transformer-based pretrained language models. We then follow this up with the concept of prompt learning or in-context learning (ICL) and discuss how it is emerging as a popular methodology replacing the conventional supervised learning workflow comprised of pretraining and fine-tuning. We outline the research challenges in ICL, which usually involves finding the correct set of examples and contexts for the purpose of guiding the LLM decoder towards effective predictions. Afterwards, a hands-on coding and demonstration session will be carried out to impart practical knowledge about LLMs and ICL to the tutorial participants.
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 149-152
Open AccessUnleashing the Power of Large Language Models: A Hands-On Tutorial
LLMs have opened up possibilities for advancing the state-of-the-art in natural language processing (NLP). In this tutorial, we present the audience with an introduction to LLMs and the associated challenges. The tutorial is structured in the following manner. First, we provide a brief preface that outlines the fundamental principles of NLP, following which, we explore the area of distributional representation learning for NLP. Then, we delve into the essential component of transformer-based pretrained language models. We then follow this up with the concept of prompt learning or in-context learning (ICL) and discuss how it is emerging as a popular methodology replacing the conventional supervised learning workflow comprised of pretraining and fine-tuning. We outline the research challenges in ICL, which usually involves finding the correct set of examples and contexts for the purpose of guiding the LLM decoder towards effective predictions. Afterwards, a hands-on coding and demonstration session will be carried out to impart practical knowledge about LLMs and ICL to the tutorial participants.