From the 1 of 4 linked papers with an AI index.
4 papers
Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents
Zining Huang, Haoran Que, Hong Zeng +8
When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in t…
MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
Xianru Chen, Yukai Huang, Mingxiang Chen +6
The paper introduces MSQA, a benchmark of over a thousand native questions in 11 languages designed to evaluate whether multilingual models also understand the cultures behind thos…
BABE: Biology Arena BEnchmark
Junting Zhou, Jin Chen, Linfeng Hao +10
The rapid evolution of large language models (LLMs) has expanded their capabilities from basic dialogue to advanced scientific reasoning. However, existing benchmarks in biology of…
Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
Shuangshuang Ying, Zheyu Wang, Yunjian Peng +16
Despite strong performance on existing benchmarks, it remains unclear whether large language models can reason over genuinely novel scientific information. Most evaluations score e…