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 specs and proofs. No few-shot method solves all stages, making it a …
We introduce CLEVER, the first curated benchmark for evaluating the generation of specifications and formally verified code in Lean. The benchmark comprises of 161 programming problems; it evaluates …
Submissions | OpenReview
Jan 22, 2025 · Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers Lorenzo Pacchiardi, Marko Tesic, Lucy G Cheke, Jose Hernandez-Orallo 27 Sept 2024 …
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 nEtwork Robustness. The proposed CLEVER score is attack-agnostic …
STAIR: Improving Safety Alignment with Introspective Reasoning
May 1, 2025 · Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods …
Contrastive Learning Via Equivariant Representation - OpenReview
Sep 25, 2024 · In this paper, we revisit the roles of augmentation strategies and equivariance in improving CL's efficacy. We propose CLeVER (Contrastive Learning Via Equivariant …
EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic ...
Sep 16, 2025 · A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like “clever but clueless interns” in novel environments. This …
Dual-Model Defense: Safeguarding Diffusion Models from Membership ...
Sep 27, 2024 · Membership inference and memorization is a key challenge with diffusion models. Mitigating such vulnerabilities is hence an important topic. The idea of using an ensemble of model is …
KnowTrace: Explicit Knowledge Tracing for Structured...
Sep 13, 2024 · TL;DR: We introduce a structured RAG paradigm (KnowTrace) that seamlessly integrates knowledge structuring and multi-step reasoning for improved MHQA performance.
579 In this paper, we have proposed a novel counter- factual framework CLEVER for debiasing fact- checking models. Unlike existing works, CLEVER is augmentation-free and mitigates biases on infer- …