SyncAI.news, a Varaisys broadcasting
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases
AK

Aditya Kumaran, Rahul Singhal, Karime Maamari, Amine Mhedhbi, Pradyumna Tambwekar

· 1 min read

ResearcharXiv cs.AI

HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases

arXiv:2609.30571v1 Announce Type: new Abstract: Language models are often evaluated on curated benchmarks that underrepresent the complexity of enterprise deployments. We introduce HARDEN, a constrained evolutionary search method to adapt the input of existing evaluation cases into more challenging variants while keeping their expected outputs fixed. HARDEN searches along generated domain-specific complexity axes while enforcing feasibility constraints such as preserving task semantics, realism, and execution validity. Across FinQA, PubMedQA, and ContractNLI and three Qwen3.5 model scales (35B-A3B, 122B-A10B, and 397B-A17B), HARDEN reduces task-model accuracy by 22.7% on average and by up to 49.9% relative to single-pass baselines using the same feasibility checks. These results show that evolutionary search can produce substantially harder valid evaluation cases.

Original source

This story was published by arXiv cs.AI and written by Aditya Kumaran, Rahul Singhal, Karime Maamari, Amine Mhedhbi, Pradyumna Tambwekar. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News