arXiv Artificial Intelligence

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

2 hours ago 28.09.2026 07:00 👁 2 views
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases

Quick summary

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

Key takeaways

  • 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.

Why it matters

“HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗