#acl-2026

The latest AI and developer news about #acl-2026, with the original source and a short summary.

LG AI Research Releases ReSQL Framework That Learns from Failure Cases

LG AI Research announced ReSQL, which utilizes execution errors as learning signals to improve Text-to-SQL performance in lightweight models.

·2·2026.08.27 17:00

LG AI Research Unveils ReSQL, a Self-Improving Text-to-SQL System That Surpasses GPT-4

LG AI Research has released ReSQL, which recycles SQL errors from lightweight models for training to outperform GPT-4.

·1·2026.08.27 17:00

[ACL 2026] From Documents to Segments: Revisiting Topic Modeling via Segment-Based Topic Assignment

LG AI Research proposed a method that assigns topics at the segment level rather than the document level to resolve distortion issues in existing topic modeling.

·2·2026.08.14 11:00

[ACL 2026] Assigning Topics to 'Segments' Instead of Documents: Redefining Topic Modeling

LG AI Research proposed the **SBTA** technique, which assigns topics to sentence-level segments instead of documents to resolve topic contamination.

·2·2026.08.14 11:00

TIME Training Method Solves Qwen's Overthinking Problem

TIME methodology and TIMEBench have been released, training Qwen models to perform short reasoning only when needed.

·2026.05.18 11:00