Papers by Manuela Veloso

11 papers
HiddenTables and PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies (2023.emnlp-main)

Copied to clipboard

Challenge: A myriad of different Large Language Models (LLMs) face a common challenge in contextually analyzing table question-answering tasks.
Approach: They propose a cooperative game that is played between the code-generating LLM "Solver" and the "Oracle" it is based on natural language schemas and ensures the security of the underlying data.
Outcome: The proposed game shows that LLMs are ineffective at generalizing and performing on complex queries, handle compositional dependencies, and align natural language to programmatic commands when concrete table schemas are provided.
LAW: Legal Agentic Workflows for Custody and Fund Services Contracts (2025.coling-industry)

Copied to clipboard

Challenge: Currently, there are limited resources available to build a legal domain-specific Large Language Model (LLM) however, legal contracts are highly varied not only in terms of semantics but also accessibility.
Approach: They propose a Large Language Model (LLM) that integrates multiple specialized agents and text agents to respond to user queries.
Outcome: The proposed model outperforms the baseline model in complex tasks such as calculating a contract’s termination date by 92.9% points.
“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.
AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations (2025.acl-long)

Copied to clipboard

Challenge: State-of-the-art multimodal web agents can perform many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs).
Approach: They propose to build multimodal web agents for few-shot adaptability using human demonstrations to improve their generalization and adaptability.
Outcome: The proposed framework enables both proprietary and open-weights multimodal web agents to adapt to new websites and domains using few human demonstrations.
Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a critical tool for time series analysis and reporting in many fields, including healthcare, finance, climate, and many more.
Approach: They propose a framework for rigorously evaluating the capabilities of Large Language Models (LLMs) on time series understanding, encompassing both univariate and multivariate forms.
Outcome: The proposed framework delineates various characteristics inherent in time series data.
LETS-C: Leveraging Text Embedding for Time Series Classification (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in language modeling have shown promising results when applied to time series data.
Approach: They propose a method to fine-tune large language models for time series classification tasks using text embedding models and a simple classification head.
Outcome: The proposed model outperforms the current SOTA model on a time series classification benchmark and uses only 14.5% of the trainable parameters.
Distill and Align Decomposition for Enhanced Claim Verification (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods for complex claim verification struggle to align decomposition quality with verification performance.
Approach: They propose a reinforcement learning approach that optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization.
Outcome: The proposed method outperforms prompt-based approaches and existing methods in six evaluation settings.
What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are often treated as defects of the model or its decoding strategy.
Approach: They construct a 22-dimension query feature vector covering clause complexity, lexical rarity, anaphora, negation, answerability, and intention grounding.
Outcome: The proposed model covers clause complexity, lexical rarity, anaphora, negation, answerability, and intention grounding, all known to affect human comprehension.
Advanced Messaging Platform (AMP): Pipeline for Automated Enterprise Email Processing (2025.acl-industry)

Copied to clipboard

Challenge: a lack of publicly available datasets for training and benchmarking limits current AI techniques' effectiveness in industry-specific applications.
Approach: They propose an email automation pipeline that automates email response generation at scale in real-world enterprise settings.
Outcome: The proposed pipeline automates email response generation at scale in real-world environments.
TASER: Table Agents for Schema-guided Extraction and Recommendation (2026.eacl-industry)

Copied to clipboard

Challenge: Real-world financial filings report critical information about an entity’s investment holdings, but they are often buried in messy, multi-page, fragmented tables that are difficult to parse.
Approach: They propose to train a system that converts highly unstructured, multi-page, heterogeneous tables into normalized, schema-conforming outputs.
Outcome: The proposed system outperforms vision-based table detection models by 10.1% and can generate more useful recommendations by 10%.

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