arXiv subjects

Leon Strelkov

Publications and source records attributed to Leon Strelkov.

2 recordsLinked to original sources

arXiv2026

Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP

Safety benchmarks for large language models (LLMs) commonly use multiple-choice question (MCQ) format. However, prior studies documented that MCQ format reduces refusal rates, which may significantly affect the safety behavior of the model. We provide a first mechanistic explanation of this effect on the Weapons of Mass Destruction Proxy (WMDP) dataset across two models - Llama-3.1-8B and Qwen3-8B. First, we use the tuned lens technique to show that when processing MCQ the model commits to an answer-letter token very quickly, which is in contrast to the gradual refusal build-up in open-ended formats. Additionally, we observe that activations on the MCQ format lie roughly 3x further from the refusal direction, compared with their open-ended counterparts. Moreover, ablating the attention heads that carry the MCQ format answer increases the refusal, which is a direct evidence that the MCQ answer-selection competes with refusal. These findings indicate that MCQ safety scores primarily measure knowledge capabilities and do not assess the safety-mechanisms.

cs.CL↗

arXiv2025

Automated Evolutionary Optimization for Resource-Efficient Neural Network Training

There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary optimization to model architecture and training strategy. PETRA includes pruning, quantization, and loss regularization. Experimental studies on real-world data with financial event sequences, as well as image and time-series -- benchmarks, demonstrate PETRA's ability to improve neural model performance and scalability -- namely, a significant decrease in model size (up to 75%) and latency (up to 33%), and an increase in throughput (by 13%) without noticeable degradation in the target metric.

cs.LG↗