Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Emergent Inference-Time Semantic Contamination via In-Context Priming
Marcin Abram
Recent work has shown that fine-tuning large language models (LLMs) on insecure code or culturally loaded numeric codes can induce emergent misalignment, causing models to produce…
cs.CY2026
Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems
Marcin Abram
We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamina…