12 citations · 19 across the 19 of their papers we have counts for
21 papers · 1 filter
Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation
Fangzheng Tian, Debasis Ganguly, Craig Macdonald
Agentic Retrieval-Augmented Generation (RAG) has become a promising paradigm for multi-hop question answering, where a reasoning model iteratively issues queries to a retriever and…
Robustness of IR Models to Collection Growth
Emmanouil Georgios Lionis, Sean MacAvaney, Debasis Ganguly
Information Retrieval (IR) systems seek to identify relevant documents within a collection. In practical applications, collections are dynamic, with documents frequently added. We…
A Theoretical Framework for Risk Analysis of Stochastic Rankers
Debasis Ganguly
Different from deterministic rankers that seek to maximize relevance at top ranks, stochastic ranking policies instead estimate distributions over permutations, from which rankings…
RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation
Fangzheng Tian, Debasis Ganguly, Craig Macdonald
Query Performance Prediction (QPP) estimates the retrieval quality of ranking models without the use of any human-assessed relevance judgements, and finds applications in query-spe…
Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents
Nilanjan Sinhababu, Soumedhik Bharati, Debasis Ganguly +1
Common approaches to reduce the computational overhead of reranking models include identifying a candidate set of documents for reranking or constructing comparison graphs to minim…
SuiteEval: Simplifying Retrieval Benchmarks
Andrew Parry, Debasis Ganguly, Sean MacAvaney
Information retrieval evaluation often suffers from fragmented practices -- varying dataset subsets, aggregation methods, and pipeline configurations -- that undermine reproducibil…
LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
Manish Chandra, Debasis Ganguly, Iadh Ounis
Most conventional Retrieval-Augmented Generation (RAG) pipelines rely on relevance-based retrieval, which often misaligns with utility -- that is, whether the retrieved passages ac…
Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation
Fangzheng Tian, Debasis Ganguly, Craig Macdonald
The quality of answers generated by large language models (LLMs) in retrieval-augmented generation (RAG) is largely influenced by the contextual information contained in the retrie…
Revisiting Query Variants: The Advantage of Retrieval Over Generation of Query Variants for Effective QPP
Fangzheng Tian, Debasis Ganguly, Craig Macdonald
Leveraging query variants (QVs), i.e., queries with potentially similar information needs to the target query, has been shown to improve the effectiveness of query performance pred…
T-Retrievability: A Topic-Focused Approach to Measure Fair Document Exposure in Information Retrieval
Xuejun Chang, Zaiqiao Meng, Debasis Ganguly
Retrievability of a document is a collection-based statistic that measures its expected (reciprocal) rank of being retrieved within a specific rank cut-off. A collection with unifo…
Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG
Fangzheng Tian, Jinyuan Fang, Debasis Ganguly +2
Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm,…
Disentangling Locality and Entropy in Ranking Distillation
Andrew Parry, Debasis Ganguly, Sean MacAvaney
The training process of ranking models involves two key data selection decisions: a sampling strategy, and a labeling strategy. Modern ranking systems, especially those for perform…
Exploring the Role of Diversity in Example Selection for In-Context Learning
Janak Kapuriya, Manit Kaushik, Debasis Ganguly +1
In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL work…
Modeling Ranking Properties with In-Context Learning
Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly +1
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 objectiv…
Is Relevance Propagated from Retriever to Generator in RAG?
Fangzheng Tian, Debasis Ganguly, Craig Macdonald
Retrieval Augmented Generation (RAG) is a framework for incorporating external knowledge, usually in the form of a set of documents retrieved from a collection, as a part of a prom…
Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model
Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly +2
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.…
Top-Down Partitioning for Efficient List-Wise Ranking
Andrew Parry, Sean MacAvaney, Debasis Ganguly
Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarge…
"In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval"
Andrew Parry, Debasis Ganguly, Manish Chandra
With the increasing ability of large language models (LLMs), in-context learning (ICL) has evolved as a new paradigm for natural language processing (NLP), where instead of fine-tu…
Exploiting Positional Bias for Query-Agnostic Generative Content in Search
Andrew Parry, Sean MacAvaney, Debasis Ganguly
In recent years, neural ranking models (NRMs) have been shown to substantially outperform their lexical counterparts in text retrieval. In traditional search pipelines, a combinati…
Evaluating the Explainability of Neural Rankers
Saran Pandian, Debasis Ganguly, Sean MacAvaney
Information retrieval models have witnessed a paradigm shift from unsupervised statistical approaches to feature-based supervised approaches to completely data-driven ones that mak…
A Deep Learning Approach for Selective Relevance Feedback
Suchana Datta, Debasis Ganguly, Sean MacAvaney +1
Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original inf…