STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs
- 2026
- ACL 2026
Paper
Publications
22 results at ACL 2026
LLMs are Brittle to Simple Code Transformations: Introducing CETBench – A Benchmark for Code-Equivalence Checking
- Neeva Oza
- Ishaan Govil
- et al.
- 2026
- ACL 2026
PaperA Survey on Evaluation of LLM-based Agents
- Asaf Yehudai
- Lilach Edelstein
- et al.
- 2026
- ACL 2026
PaperPO-KGQA: Preference Optimization for Low-Resource Complex Knowledge Graph Question Answering
- Prerna Agarwal
- Ayushman Singh
- et al.
- 2026
- ACL 2026
PaperBeyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning
- Massimiliano Pronesti
- Anya Belz
- et al.
- 2026
- ACL 2026
PaperAutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis
- Massimiliano Pronesti
- Angelo Miculescu
- et al.
- 2026
- ACL 2026
Demo paperCARES: Context-Aware Resolution Selector for VLMs
- Moshe Kimhi
- Nimrod Shabtay
- et al.
- 2026
- ACL 2026
Workshop paperSemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
- Nedjma Ousidhoum
- Junho Myung
- et al.
- 2026
- ACL 2026
Workshop paperGeneralization in Graph Reasoning: A Systematic Comparison of LLM Training Approaches
- Sola Shirai
- Kavitha Srinivas
- et al.
- 2026
- ACL 2026
Workshop paperThe Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs
- Shir Ashury Tahan
- Yifan Mai
- et al.
- 2026
- ACL 2026
Workshop paper