Papers by Sandeep Tata

5 papers
PRISM: Efficient Long-Range Reasoning With Short-Context LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Existing solutions to long-range language tasks require large compute budgets and complex task-specific design choices.
Approach: They propose an in-context method that uses structured schemas to generate short-contemporary outputs.
Outcome: a new in-context method outperforms baselines on diverse tasks with 4x shorter contexts . it scales down to tiny contexts without increasing costs or sacrificing quality .
SUMIE: A Synthetic Benchmark for Incremental Entity Summarization (2025.coling-main)

Copied to clipboard

Challenge: Existing datasets that test incrementally update entity summaries are lacking.
Approach: They propose a fully synthetic dataset that exposes real-world IES challenges by generating diverse attributes, summaries, and unstructured paragraphs with 99% alignment accuracy.
Outcome: The proposed dataset shows that state-of-the-art LLMs struggle to update summaries with an F1 higher than 80.4%.
Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models (2023.emnlp-main)

Copied to clipboard

Challenge: a key bottleneck in developing automatic extraction models for visually rich documents is the cost of acquiring labeled documents.
Approach: They propose selective labeling to provide "yes/no" labels for candidate extractions predicted by a model trained on partially labeled documents.
Outcome: The proposed method reduces the cost of acquiring labeled data by 10 with a negligible loss in accuracy.
Representation Learning for Information Extraction from Form-like Documents (2020.acl-main)

Copied to clipboard

Challenge: Form-like documents like invoices, purchase orders, tax forms and insurance quotes are common in day-to-day business workflows, but current techniques for processing them largely still employ manual effort or brittle and error-prone heuristics for extraction.
Approach: They propose an extraction system that uses knowledge of the types of the target fields to generate extraction candidates and a neural network architecture that learns a dense representation of each candidate based on neighboring words in the document.
Outcome: The proposed system generates extraction candidates based on neighboring words in the document and is interpretable, as shown using loss cases.
Enhancing Incremental Summarization with Structured Representations (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models struggle with processing extensive input contexts, leading to redundancy or incoherency.
Approach: They propose a chain-of-key update based on JSON structured memory representations to improve summarization performance by 40% and 14% on two public datasets.
Outcome: The proposed method improves summarization performance by 40% and 14% on two datasets.

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