Papers by Prateek Gupta

9 papers
NEST: Nested Evidence Survival for Retrieval (2026.acl-industry)

Copied to clipboard

Challenge: Existing approaches to retrieval-augmented generation (RAG) rely on rigid heuristics or computational overhead.
Approach: They propose a lightweight, training-free RAG framework that separates recall amplification from precision selection.
Outcome: Evaluated on WebQuestions, HotpotQA and internalQA benchmarks, NEST outperforms strong adaptive RAG baselines.
Building a Word Segmenter for Sanskrit Overnight (L18-1)

Copied to clipboard

Challenge: Sanskrit word segmentation is challenging due to the issue of Sandhi . digitisation efforts have made the manuscripts available in the public domain .
Approach: They propose a deep sequence to sequence model that takes only the sandhied string as input and predicts the unsandhized string.
Outcome: The proposed model improves on the current state of the art by 16.79% . the system can be trained "overnight" and be used for production .
SELENE: Selective and Evidence-Weighted LLM Debating for Efficient and Reliable Reasoning (2026.eacl-industry)

Copied to clipboard

Challenge: Existing multi-agent debate frameworks are computationally expensive and prone to degradation under pro-longed debates due to redundant exchanges and unstable judging.
Approach: They propose a framework that unifies Selective Debate Initiation (SDI) with Evidence Weighted Self-Consistency (EWSC) for adaptive, debate-on-demand reasoning.
Outcome: Evaluated on BoolQ, CosmosQA, and an internal QnA benchmark, the proposed framework achieves higher factual robustness and efficiency.
Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant (2026.acl-industry)

Copied to clipboard

Challenge: Qualitative research emphasizes constructing meaning through iterative engagement with textual data.
Approach: They present and benchmark a qualitative research assistant system that allows researchers to identify themes and annotate datasets.
Outcome: The proposed system achieves an inter-rater reliability between Muse and humans of Cohen’s = 0.7 for well-specified codes.
Revisiting In-Context Learning with Long Context Language Models (2025.findings-acl)

Copied to clipboard

Challenge: In-Context Learning (ICL) is a technique by which language models make predictions based on examples provided in their input context.
Approach: They revisited previous studies using in-context learning techniques . they found that using a data augmentation approach, they significantly improved ICL performance .
Outcome: The proposed approach significantly improves ICL performance on 18 datasets spanning 4 tasks . the proposed approach does not improve performance over a simple random sample selection method .
Distantly Supervised Aspect Clustering And Naming For E-Commerce Reviews (2022.naacl-industry)

Copied to clipboard

Challenge: Product aspect extraction from reviews is a critical task for e-commerce services . scale of reviews makes human review at ecommerce scale infeasible.
Approach: They propose automated methods for extracting aspect phrases from reviews . they train transformer based sentence embeddings that are aware of unique e-commerce language characteristics .
Outcome: The proposed method improves the Silhouette Score by 64% compared to the state-of-the-art model . human review at e-commerce scale is infeasible due to the scale of the reviews .
ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation (2026.eacl-industry)

Copied to clipboard

Challenge: Existing methods for retrieval-augmented generation (RAG) fail to assess evidence sufficiency, detect subtle mismatches or reduce redundancy.
Approach: They propose a lightweight yet reasoning-driven architecture that enhances factual grounding . ReflectiveRAG employs self-reflective retrieval and Contrastive noise removal .
Outcome: a new architecture improves factual grounding by using self-reflective retrieval and Contrastive noise removal.
Break-Ideate-Generate (BrIdGe): Moving beyond Translations for Localization using LLMs (2025.naacl-industry)

Copied to clipboard

Challenge: Traditional methods of localization focus on linguistic conversion, but content needs to align with the target audience’s cultural norms, nuances, and technical requirements.
Approach: They propose a new approach for Large Languages Models (LLMs) called Break-Ideate-Generate (BrIdGe) that breaks the source content into granular facts, organizes the granules and executes the plan to ‘generate’ localized content.
Outcome: The proposed approach 'breaks' the source content into granular facts, ‘ideates’ an action plan for content creation in the target language by organizing the granules, and finally executes the plan to ‘generate’ localized content.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations