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 …

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 …

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 …

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 …

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...

ACII 2021 CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems Kushal Chawla, Jaysa Ramirez, Rene Clever, Gale M. Lucas, Jonathan May, Jonathan Gratch 2021 …

Feb 15, 2018 · We propose the first attack-independent robustness metric, a.k.a CLEVER, that can be applied to any neural network classifier.

Oct 12, 2024 · Keywords: histopathology, foundation models, batch effects, Clever Hans effect, robustness, generalization Abstract: Deep learning has led to remarkable advancements in …

Sep 26, 2024 · TL;DR: This paper proposes CLeVER, a novel equivariant-based contrastive learning framework that improves training efficiency and robustness in downstream tasks by incorporating …

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- …