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 …
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; …
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 prompts, often referred to as jailbreak attacks, which can …
Dual-Model Defense: Safeguarding Diffusion Models from …
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 …
Measuring Mathematical Problem Solving With the MATH Dataset
Oct 18, 2021 · Abstract: Many intellectual endeavors require mathematical problem solving, but this skill remains beyond the capabilities of computers. To measure this ability in machine …
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.
LLaVA-OneVision: Easy Visual Task Transfer | OpenReview
Feb 10, 2025 · We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the …
La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse...
May 1, 2025 · We use a clever technique that involves rotating the data within each layer of the model, making it easier to identify and keep only the most important parts for processing. This …
Deep Think with Confidence - OpenReview
Sep 17, 2025 · The online mode with adaptive sampling and warmup is a clever way to approximate offline performance in real-time, making it suitable for serving frameworks. …
Reasoning of Large Language Models over Knowledge Graphs with...
Jan 22, 2025 · While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate. …