arXiv subjects

Debasis Ganguly

Publications and source records attributed to Debasis Ganguly.

At least 19 recordsLinked to original sources

arXiv2026

Robustness of IR Models to Collection Growth

Information Retrieval (IR) systems seek to identify relevant documents within a collection. In practical applications, collections are dynamic, with documents frequently added. We argue that ideally, a retriever's effectiveness should not decrease when non-relevant documents are added to a collection. This study formalises this concept and empirically evaluates it by merging two collections with negligible topic overlap. We hypothesise that the way an IR model conditions its ranking on other documents in a collection (e.g., the IDF component in BM25 or contextual documents in listwise rerankers) plays an important role in its robustness to the addition of non-relevant documents. We broadly classify models as those that do not depend on other documents (Multi-Document-Agnostic, MDA) and those that do (Multi-Document-Dependent, MDD). Our results show that neither MDD nor MDA models are fully robust to the addition of non-relevant documents, as all models exhibit some performance degradation. Interestingly, among the models we test, MDA is more effective than MDD for retrieval, whereas MDD and MDA rerankers are equally effective.

cs.IR↗

arXiv2026

Annotating Topical Legal Insights from Case Proceedings

In this paper, we mainly concentrate on finding concepts or topics from the legal case proceedings, since adopting a structured representation for legal documents, as opposed to a mere bag-of-words flat text representation, can significantly enhance processing capabilities. To achieve this objective, we put forward a set of diverse concepts for legal case proceedings. With this motivation, we propose LeDA, a system for Legal Data Annotation. The system offers the generic functionality of annotating and adjudicating entities or concepts within documents via a web-based interface. A novel feature of our system is that it allows to dynamic create new tags for annotation, which is a particularly useful provision for situations where there exists no pre-defined ontology for the entities (concepts) that need to be annotated - these being rather discovered by annotators as they continue examining more documents. The system that we demonstrate is currently in use to annotate a set of concepts from legal documents to construct semantic representations of documents as bags of concepts that can then be used for several downstream tasks, such as prior case retrieval, judgment prediction, and so on. Along with the system features in general, we also describe how LeDA was used by 3 assessors to annotate and adjudicate legal concept names from Indian Supreme Court case proceedings.

cs.AI↗

arXiv2026

Towards a Relevance Posterior in Neural Information Access

Modern information retrieval systems typically operationalise relevance as a query-conditional score computed at inference time. This design choice has become dominant such that alternative decompositions of relevance are rarely discussed, despite the long history of document and query priors in probabilistic retrieval and large-scale search. As neural ranking models grow more computationally expensive and retrieval pipelines expand to include multi-stage ranking, recommendation, and retrieval-augmented generation, this monolithic view of query-time scoring becomes increasingly limiting. We argue that modern information access systems are more naturally understood as performing approximate posterior inference, in which relevance is refined through a staged combination of query-dependent likelihoods and query-independent priors. We extend classical probabilistic retrieval formalisms to contemporary learned systems and show how explicit likelihood-prior decomposition exposes new opportunities to shift computation offline while disentangling document-level and interaction-level beliefs. We present empirical evidence that incorporating query-independent document utility can complement existing rankers and improve effectiveness with minimal query-time computation (solely score fusion). Concretely, a learned prior improves first-stage retrieval through rank fusion (up to 0.046 nDCG@10 on TREC DL-2019 and 0.029 nDCG@10 on TREC DL-2020) and also improves downstream re-ranking, with the largest gains observed for the LLM re-ranker RankZephyr (up to 0.054 nDCG@10 on TREC DL-2020). Finally, we discuss how this decomposition connects to broader information access and outline research directions for designing retrieval systems that explicitly allocate modelling capacity between offline priors and online interaction.

cs.IR↗

arXiv2026

A Theoretical Framework for Risk Analysis of Stochastic Rankers

Different from deterministic rankers that seek to maximize relevance at top ranks, stochastic ranking policies instead estimate distributions over permutations, from which rankings are sampled, towards obtaining diversified or fair exposure. Such policies are commonly evaluated in terms of expected effectiveness postreranking. However, the randomness inherent in these policies gives rise to a fundamental but under-explored ex ante question: prior to applying stochastic reranking, how large can the induced variation in retrieval effectiveness be in the worst case? This paper presents a theoretical analysis of reranking risk, defined as the maximum absolute change in discounted cumulative gain (DCG) resulting from a permutation sampled from a stochastic reranking policy applied to a fixed retrieved list.We derive that this risk is governed by the distribution of the recall points in the initial retrieved list. We conduct experiments on submitted runs from the TREC Fairness 2022 track that employ stochastic reranking policies and empirically demonstrate that the effectiveness variations predicted by our theory closely approximate the observed changes in DCG.

cs.IR↗

arXiv2026

RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation

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-specific selective decision making to improve overall retrieval effectiveness. Although unsupervised QPP approaches are effective for lexical retrieval models, they usually perform weaker for neural rankers. Recent work shows that leveraging query variants (QVs), i.e., queries with potentially similar information needs to a given query, can enhance unsupervised QPP accuracy. However, existing QV-based prediction methods rely on query variants generated by term expansion of the input query, which is likely to yield incoherent, hallucinatory and off-topic QVs. In this paper, we propose to make use of queries retrieved from a log of past queries as QVs to be subsequently used for QPP. In addition to directly applying retrieved QVs in QPP, we further propose to leverage large language models (LLMs) to generate QVs conditioned on the retrieved QVs, thus mitigating the limitation of relying only on existing queries in a log. Experiments on TREC DL'19 and DL'20 show that QPP enhanced with RAQG outperform the best-performing existing QV-based prediction approach by as much as 30% on neural ranking models such as MonoT5.

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↗

arXiv2026

SuiteEval: Simplifying Retrieval Benchmarks

Information retrieval evaluation often suffers from fragmented practices -- varying dataset subsets, aggregation methods, and pipeline configurations -- that undermine reproducibility and comparability, especially for foundation embedding models requiring robust out-of-domain performance. We introduce SuiteEval, a unified framework that offers automatic end-to-end evaluation, dynamic indexing that reuses on-disk indices to minimise disk usage, and built-in support for major benchmarks (BEIR, LoTTE, MS MARCO, NanoBEIR, and BRIGHT). Users only need to supply a pipeline generator. SuiteEval handles data loading, indexing, ranking, metric computation, and result aggregation. New benchmark suites can be added in a single line. SuiteEval reduces boilerplate and standardises evaluations to facilitate reproducible IR research, as a broader benchmark set is increasingly required.

cs.IR↗

arXiv2026

LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG

Most conventional Retrieval-Augmented Generation (RAG) pipelines rely on relevance-based retrieval, which often misaligns with utility -- that is, whether the retrieved passages actually improve the quality of the generated text specific to a downstream task such as question answering or query-based summarization. The limitations of existing utility-driven retrieval approaches for RAG are that, firstly, they are resource-intensive typically requiring query encoding, and that secondly, they do not involve listwise ranking loss during training. The latter limitation is particularly critical, as the relative order between documents directly affects generation in RAG. To address this gap, we propose Lightweight Utility-driven Reranking for Efficient RAG (LURE-RAG), a framework that augments any black-box retriever with an efficient LambdaMART-based reranker. Unlike prior methods, LURE-RAG trains the reranker with a listwise ranking loss guided by LLM utility, thereby directly optimizing the ordering of retrieved documents. Experiments on two standard datasets demonstrate that LURE-RAG achieves competitive performance, reaching 97-98% of the state-of-the-art dense neural baseline, while remaining efficient in both training and inference. Moreover, its dense variant, UR-RAG, significantly outperforms the best existing baseline by up to 3%.

cs.IR↗

arXiv2026

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.

cs.IR↗

arXiv2026

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.

cs.IR↗

arXiv2026

Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation

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 retrieved documents. A key challenge for improving RAG is to predict both the utility of retrieved documents -- quantified as the performance gain from using context over generation without context -- and the quality of the final answers in terms of correctness and relevance. In this paper, we define two prediction tasks within RAG. The first is retrieval performance prediction (RPP), which estimates the utility of retrieved documents. The second is generation performance prediction (GPP), which estimates the final answer quality. We hypothesise that in RAG, the topical relevance of retrieved documents correlates with their utility, suggesting that query performance prediction (QPP) approaches can be adapted for RPP and GPP. Beyond these retriever-centric signals, we argue that reader-centric features, such as the LLM's perplexity of the retrieved context conditioned on the input query, can further enhance prediction accuracy for both RPP and GPP. Finally, we propose that features reflecting query-agnostic document quality and readability can also provide useful signals to the predictions. We train linear regression models with the above categories of predictors for both RPP and GPP. Experiments on the Natural Questions (NQ) dataset show that combining predictors from multiple feature categories yields the most accurate estimates of RAG performance.

cs.IR↗

arXiv2025

Revisiting Query Variants: The Advantage of Retrieval Over Generation of Query Variants for Effective QPP

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 prediction (QPP) approaches. Existing QV-based QPP methods generate QVs facilitated by either query expansion or non-contextual embeddings, which may introduce topical drifts and hallucinations. In this paper, we propose a method that retrieves QVs from a training set (e.g., MS MARCO) for a given target query of QPP. To achieve a high recall in retrieving queries with the most similar information needs as the target query from a training set, we extend the directly retrieved QVs (1-hop QVs) by a second retrieval using their denoted relevant documents (which yields 2-hop QVs). Our experiments, conducted on TREC DL'19 and DL'20, show that the QPP methods with QVs retrieved by our method outperform the best-performing existing generated-QV-based QPP approaches by as much as around 20\%, on neural ranking models like MonoT5.

cs.IR↗

arXiv2025

HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers

Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization.

cs.IR↗

arXiv2025

T-Retrievability: A Topic-Focused Approach to Measure Fair Document Exposure in Information Retrieval

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 uniformly distributed retrievability scores across documents is an indicator of fair document exposure. While retrievability scores have been used to quantify the fairness of exposure for a collection, in our work, we use the distribution of retrievability scores to measure the exposure bias of retrieval models. We hypothesise that an uneven distribution of retrievability scores across the entire collection may not accurately reflect exposure bias but rather indicate variations in topical relevance. As a solution, we propose a topic-focused localised retrievability measure, which we call \textit{T-Retrievability} (topic-retrievability), which first computes retrievability scores over multiple groups of topically-related documents, and then aggregates these localised values to obtain the collection-level statistics. Our analysis using this proposed T-Retrievability measure uncovers new insights into the exposure characteristics of various neural ranking models. The findings suggest that this localised measure provides a more nuanced understanding of exposure fairness, offering a more reliable approach for assessing document accessibility in IR systems.

cs.IR↗

arXiv2025

Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG

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, exemplified by recent research works such as Search-R1, enables the model to decide when to search and obtain external information. However, the queries generated by such Agentic RAG models and the role of the retriever in obtaining high-quality answers remain understudied. To this end, this initial study examines the applicability of query performance prediction (QPP) within the recent Agentic RAG models Search-R1 and R1-Searcher. We find that applying effective retrievers can achieve higher answer quality within a shorter reasoning process. Moreover, the QPP estimates of the generated queries, used as an approximation of their retrieval quality, are positively correlated with the quality of the final answer. Ultimately, our work is a step towards adaptive retrieval within Agentic RAG, where QPP is used to inform the model if the retrieved results are likely to be useful.

cs.IR↗

arXiv2025

In-Context Learning as an Effective Estimator of Functional Correctness of LLM-Generated Code

When applying LLM-based code generation to software development projects that follow a feature-driven or rapid application development approach, it becomes necessary to estimate the functional correctness of the generated code in the absence of test cases. Just as a user selects a relevant document from a ranked list of retrieved ones, a software generation workflow requires a developer to choose (and potentially refine) a generated solution from a ranked list of alternative solutions, ordered by their posterior likelihoods. This implies that estimating the quality of a ranked list -- akin to estimating "relevance" for query performance prediction (QPP) in IR -- is also crucial for generative software development, where quality is defined in terms of "functional correctness". In this paper, we propose an in-context learning (ICL) based approach for code quality estimation. Our findings demonstrate that providing few-shot examples of functionally correct code from a training set enhances the performance of existing QPP approaches as well as a zero-shot-based approach for code quality estimation.

cs.SE↗

arXiv2025

Disentangling Locality and Entropy in Ranking Distillation

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 performing semantic search, typically use a ``hard negative'' sampling strategy to identify challenging items using heuristics and a distillation labeling strategy to transfer ranking "knowledge" from a more capable model. In practice, these approaches have grown increasingly expensive and complex, for instance, popular pretrained rankers from SentenceTransformers involve 12 models in an ensemble with data provenance hampering reproducibility. Despite their complexity, modern sampling and labeling strategies have not been fully ablated, leaving the underlying source of effectiveness gains unclear. Thus, to better understand why models improve and potentially reduce the expense of training effective models, we conduct a broad ablation of sampling and distillation processes in neural ranking. We frame and theoretically derive the orthogonal nature of model geometry affected by example selection and the effect of teacher ranking entropy on ranking model optimization, establishing conditions in which data augmentation can effectively improve bias in a ranking model. Empirically, our investigation on established benchmarks and common architectures shows that sampling processes that were once highly effective in contrastive objectives may be spurious or harmful under distillation. We further investigate how data augmentation, in terms of inputs and targets, can affect effectiveness and the intrinsic behavior of models in ranking. Through this work, we aim to encourage more computationally efficient approaches that reduce focus on contrastive pairs and instead directly understand training dynamics under rankings, which better represent real-world settings.

cs.IR↗

arXiv2025

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 (Touch\'e), 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↗