Jul 8, 2025 · We introduce ${\\rm C{\\small LEVER}}$, a high-quality, manually curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task …

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 …

Promoting openness in scientific communication and the peer-review process

Sep 18, 2025 · This paper introduces CLEVER, a benchmark dataset designed to evaluate LLMs on formally verified code generation. It consists of 161 carefully crafted Lean specifications derived from …

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- …

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 …

Feb 21, 2026 · This survey on spurious correlations uses the Clever Hans metaphor to motivate the problem, formalizes a group-based setup g=(y,a) with core metrics (worst-group, average-group, bias …

May 1, 2025 · One common approach is training models to refuse unsafe queries, but this strategy can be vulnerable to clever prompts, often referred to as jailbreak attacks, which can trick the AI into …

While, as we mentioned earlier, there can be thorny “clever hans” issues about humans prompting LLMs, an automated verifier mechanically backprompting the LLM doesn’t suffer from these. We …

Jan 26, 2026 · The story of this paper is reasonable, and the design is clever. The proposed method does not modify or fine-tune the base generator. Training only the small policy heads with GRPO is …