arXiv subjects

Nilanjan Sinhababu

Publications and source records attributed to Nilanjan Sinhababu.

5 recordsLinked to original sources

arXiv2026

Modeling Ranking Properties with In-Context Learning

While standard IR models are primarily designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly addressed using post-hoc heuristics or supervised learning methods, which require task-specific training for each ranking scenario and dataset. In this work, we propose an in-context learning (ICL) approach for listwise LLM rerankers that eliminates the need for such training. Instead, our method relies on a small number of example rankings that demonstrate the desired trade-offs between objectives for past queries similar to the current input. We evaluate our approach on common IR test collections to investigate multiple auxiliary objectives: group fairness (TREC Fairness), polarity diversity (Touché), and topical diversity (TREC Deep Learning 2019/2020). We empirically validate that our method enables control over ranking behavior through demonstration engineering, allowing nuanced behavioral adjustments without explicit optimization. Our experiment demonstrates significant improvements in auxiliary objectives, with up to 23\% in topical diversity and 20.6\% fairness gains across different tasks, while maintaining relevance across benchmarks.

cs.IR↗

arXiv2026

Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents

Common approaches to reduce the computational overhead of reranking models include identifying a candidate set of documents for reranking or constructing comparison graphs to minimize redundant comparisons. For pointwise rankers, determining a candidate set typically involves estimating a query-dependent cutoff based on the scores of the top-ranked documents. In contrast, comparison graphs for listwise approaches are often derived using heuristics, such as propagating local comparisons within sliding windows in a bottom-up fashion or reducing comparisons via pivot-based strategies in a top-down manner. In this work, we argue that restricting these processes to existing documents in the collection is unnecessary. Instead, we propose leveraging the generative capabilities of large language models to synthesize a pseudo-relevant document for a given query. We then adapt existing reranking approaches and also propose a novel parallel reranking approach to leverage this LLM-generated document as a pivot. Our experiments demonstrate that using LLM-generated pivots for ranked list truncation reduces the number of pointwise ranker inferences by up to 66\%. In both in-domain and out-of-domain settings, we observe speedups of up to $2.95\times$ in listwise reranking, while maintaining comparable or improved retrieval effectiveness.

cs.IR↗

arXiv2024

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that are capable of working in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline.

cs.IR↗

arXiv2021

Computational Intelligence Approach to Improve the Classification Accuracy of Brain Neoplasm in MRI Data

Automatic detection of brain neoplasm in Magnetic Resonance Imaging (MRI) is gaining importance in many medical diagnostic applications. This report presents two improvements for brain neoplasm detection in MRI data: an advanced preprocessing technique is proposed to improve the area of interest in MRI data and a hybrid technique using Convolutional Neural Network (CNN) for feature extraction followed by Support Vector Machine (SVM) for classification. The learning algorithm for SVM is modified with the addition of cost function to minimize false positive prediction addressing the errors in MRI data diagnosis. The proposed approach can effectively detect the presence of neoplasm and also predict whether it is cancerous (malignant) or non-cancerous (benign). To check the effectiveness of the proposed preprocessing technique, it is inspected visually and evaluated using training performance metrics. A comparison study between the proposed classification technique and the existing techniques was performed. The result showed that the proposed approach outperformed in terms of accuracy and can handle errors in classification better than the existing approaches.

cs.CV↗

arXiv2021

Medical Information Retrieval and Interpretation: A Question-Answer based Interaction Model

The Internet has become a very powerful platform where diverse medical information are expressed daily. Recently, a huge growth is seen in searches like symptoms, diseases, medicines, and many other health related queries around the globe. The search engines typically populate the result by using the single query provided by the user and hence reaching to the final result may require a lot of manual filtering from the user's end. Current search engines and recommendation systems still lack real time interactions that may provide more precise result generation. This paper proposes an intelligent and interactive system tied up with the vast medical big data repository on the web and illustrates its potential in finding medical information.

cs.MA↗