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 …

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 22, 2025 · Promoting openness in scientific communication and the peer-review process

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 …