
Evaluating the Robustness of Neural Networks: An Extreme Value...
Feb 15, 2018 · Our analysis yields a novel robustness metric called CLEVER, which is short for Cross Lipschitz Extreme Value for …
The Clever Hans Mirage: A Comprehensive Survey on Spurious...
Feb 21, 2026 · The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning Wenqian Ye, …
Djork-Arné Clevert | OpenReview
Promoting openness in scientific communication and the peer-review process
We use CLEVER to evaluate several state-of-the-art LLMs prompted in a few-shot manner and show that they can only solve up to …
CLEVER: A Curated Benchmark for Formally Verified Code Generation
Jul 8, 2025 · TL;DR: We introduce CLEVER, a hand-curated benchmark for verified code generation in Lean. It requires full formal …
CLEVER: A Curated Benchmark for Formally Verified Code Generation
Sep 18, 2025 · TL;DR: We introduce CLEVER, a hand-curated benchmark for verified code generation in Lean. It requires full formal …
While, as we mentioned earlier, there can be thorny “clever hans” issues about humans prompting LLMs, an automated verifier …
STAIR: Improving Safety Alignment with Introspective Reasoning
May 1, 2025 · One common approach is training models to refuse unsafe queries, but this strategy can be vulnerable to clever …
Shiqi Pan - OpenReview
Promoting openness in scientific communication and the peer-review process
Abstract Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale …