Papers with synthesis methods

6 papers
On the Intractability to Synthesize Factual Inconsistencies in Summarization (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods for detecting factual inconsistencies in abstractive summarization are lacking in factual consistency detection.
Approach: They propose to use real model-generated summaries with human annotations to detect factual inconsistencies.
Outcome: The proposed model outperforms the SOTA on CoGenSumm, FactCC, Frank, and SummEval datasets.
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech (2026.acl-long)

Copied to clipboard

Challenge: Existing synthesis methods cannot guarantee data quality.
Approach: They propose a hierarchical reward that balances translation quality and latency objectives by combining supervised fine-tuning data with supervised inputs.
Outcome: The proposed model can reuse key-value caches across both modalities and eliminate redundant feature recomputation.
RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods for generating high-quality reasoning data are limited in quality and availability.
Approach: They propose a method that constructs mathematical operations and generates verifiable graphs that are back-translated into complex problems.
Outcome: The proposed method achieves a 6.3% performance gain over existing methods on LLaMA-3-8B and outperforms others with only half the training data (50k vs. 100k).
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Copied to clipboard

Challenge: Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach: They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome: The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.
Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are a cost-effective and time-consuming way to capture public opinion and behavior, but their outputs are often biased and yield invalid estimates.
Approach: They propose to use large language models to generate survey responses and rectification methods that debias population estimates to find out how human responses are best allocated between them.
Outcome: The proposed methods reduce bias below 5% and increase sample size by up to 14% under a fixed budget.
HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions (2026.acl-long)

Copied to clipboard

Challenge: Multi-Hop Question Answering (MHQA) is a critical benchmark for evaluating the model’s ability to integrate information from diverse sources.
Approach: They propose a framework that synthesizes authentic multi-hop questions without manual annotation without the need for manual guidance.
Outcome: The proposed framework synthesizes bridge and comparison questions without human intervention and achieves comparable or superior quality to human-annotated datasets at a lower cost.

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