Papers with semantic validation
The AI Committee: A Multi-Agent Framework for Automated Validation and Remediation of Web-Sourced Data (2026.eacl-demo)
Copied to clipboard
| Challenge: | largelanguage models (LLMs)-powered web agents can be useful for research in areas such as social science, public health, and economics. |
| Approach: | They propose a model-agnostic multi-agent system that auto-mates the process of validating and remediatingweb-sourced datasets. |
| Outcome: | The proposed system outperforms baseline approaches and achieves datacompleteness and precision up to 73.3%. |
GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL (2026.acl-long)
Copied to clipboard
| Challenge: | Existing frameworks for Text2SQL generation still have a critical semantic gap . a dedicated validator translates generated SQL back into natural language and checks whether its logic is aligned with the original question. |
| Approach: | They propose a framework that introduces Guided Generation with SQL2Text Back-translation Validation . dedicated validator translates generated SQL back into natural language and checks whether logic is aligned with original question . |
| Outcome: | The proposed framework achieves 63.23% execution accuracy on the BIRD benchmark and 90.42% on repaired BIDR dev. |
PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction (2025.findings-acl)
Copied to clipboard
| Challenge: | a probabilistic multi-task meta-model for key information extraction is proposed . entity-level models capture spatial and visual cues, while fine-grained token classification models capture logical dependencies. |
| Approach: | They propose a probabilistic multi-task meta-model that integrates fine-grained token classification and coarse-grain entity extraction models. |
| Outcome: | The proposed model outperforms state-of-the-art models and a stacked ensemble on two datasets. |