From the 2 of 65 linked papers with an AI index.
65 papers
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Yu-Du Feng, Niels Mündler-Sasahara, Mark Vero +1
The paper proposes a cheap method to adapt reasoning language models to new tasks by first instruction‑tuning them on ordinary supervised data and then merging the tuned model back…
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Niels Mündler-Sasahara, Hristo Venev, Dawn Song +2
The paper introduces generative compilation, a method that gives compiler feedback on incomplete code during AI generation by converting partial programs into complete ones that st…
Adaptive Generation of Bias-Eliciting Questions for LLMs
Robin Staab, Jasper Dekoninck, Maximilian Baader +1
Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide. Despite their widespread adoption, growing relia…
SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics
Nikolay Georgiev, Maria Drencheva, Kseniia Ibragimova +3
As agentic AI systems tackle more complex mathematical tasks, they increasingly rely on information retrieval (IR) to search problem databases, theorem libraries, and educational r…
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
Ivo Petrov, Jasper Dekoninck, Dimitar I. Dimitrov +1
Large language models (LLMs) have become capable mathematical problem-solvers, often producing correct proofs for challenging problems. However, correctness alone is not sufficient…
Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean
Kári Rögnvaldsson, Chenhao Sun, Jasper Dekoninck +1
Large language models (LLMs) are increasingly used in workflows for generating formal proofs in Lean. These workflows often decompose problems into smaller lemmas, sample many proo…