6 papers
Towards a Relevance Posterior in Neural Information Access
Andrew Parry, Emmanouil Georgios Lionis, Debasis Ganguly +1
Modern information retrieval systems typically operationalise relevance as a query-conditional score computed at inference time. This design choice has become dominant such that al…
Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework
Payel Santra, Partha Basuchowdhuri, Debasis Ganguly
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…
Beyond Correlations: A Downstream Evaluation Framework for Query Performance Prediction
Payel Santra, Partha Basuchowdhuri, Debasis Ganguly
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, n…
HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
Payel Santra, Madhusudan Ghosh, Debasis Ganguly +2
Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). Howe…
In-Context Learning as an Effective Estimator of Functional Correctness of LLM-Generated Code
Susmita Das, Madhusudan Ghosh, Priyanka Swami +2
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 th…
One size doesn't fit all: Predicting the Number of Examples for In-Context Learning
Manish Chandra, Debasis Ganguly, Iadh Ounis
In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectiv…