Papers by Pranav Shetty

8 papers
“What is the value of templates?” Rethinking Document Information Extraction Datasets for LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing work on prompt-response datasets for visually rich document understanding (VRDU) is labor-intensive.
Approach: They propose a set of questions that are transformed from a key information extraction template to a prompt-response format using a plethora of bespoke templates.
Outcome: The proposed datasets are compared with baseline models on K2Q with zero-shot prompting.
ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images (2026.eacl-long)

Copied to clipboard

Challenge: Existing models for structured information extraction are limited by narrow entity ontologies, simple queries, or homogeneous document types.
Approach: They propose a benchmark dataset for structured Information Extraction (IE) from document images . they analyze open and closed VLMs on this benchmark .
Outcome: The proposed model can perform fine-grained structured extraction across document types and schemas.
CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation (2025.acl-long)

Copied to clipboard

Challenge: LLMs can provide key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfaithful, ungrounded, or hallucinatory outputs.
Approach: They propose a Confidence-guided copy-based decoding strategy that dynamically interpolates the model produced vocabulary distribution with a distribution derived based on copying from the context.
Outcome: The proposed method outperforms existing context-aware decoding methods on five legal benchmarks.
BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition (2021.acl-long)

Copied to clipboard

Challenge: Existing NER models are supervised by a large number of training sequences, each pre-annotated with token-level labels.
Approach: They propose a conditional hidden Markov model which can effectively infer true labels from multi-source noisy labels in an unsupervised way.
Outcome: The proposed model outperforms state-of-the-art weakly supervised NER models on four benchmarks from various domains.
Where is this coming from? Making groundedness count in the evaluation of Document VQA models (2025.findings-naacl)

Copied to clipboard

Challenge: Document Visual Question Answering (VQA) models have come close to or matching human performance on some benchmarks.
Approach: They propose a method that accounts for the semantic and multimodal groundedness of a model’s outputs and can be parameterized so that users can configure the score according to their preferences.
Outcome: The proposed method produces scores that are a better indicator of a model’s robustness and tends to give higher rewards to better-calibrated answers.
Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning (2022.acl-long)

Copied to clipboard

Challenge: Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manual designing a comprehensive, high-quality set of labeling rules is tedious and difficult.
Approach: They propose a weakly-supervised learning model that iterates and discovers new labeling rules from data to improve the WSL model.
Outcome: The proposed model outperforms state-of-the-art models on four tasks and bridges the gaps with fully supervised models.
POLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature (2024.naacl-long)

Copied to clipboard

Challenge: SciIE datasets for polymer materials are lacking for this class of materials . POLYIE is curated from 146 full-length polymer scholarly articles .
Approach: They propose a SciIE dataset for polymer materials that uses entity annotations from 146 full-length articles.
Outcome: The proposed dataset is curated from 146 full-length polymer scholarly articles . it presents challenges due to diverse lexical formats of entities and ambiguity between entities .
Detecting Non-Membership in LLM Training Data via Rank Correlations (2026.eacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are trained on increasingly vast and opaque text corpora.
Approach: They propose a test that detects dataset-level non-membership using only grey-box access to model logits.
Outcome: The proposed test detects dataset-level non-membership using only grey-box access to model logits.

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