# LLM Novice Uplift on Dual-Use, In Silico Biology Tasks

arXiv: https://arxiv.org/abs/2602.23329 · HTML: https://mlsanity.com/paper/2602.23329/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2026.

## Built on by (most cited first, 5 of 5)

- [Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants](https://mlsanity.com/paper/2607.13039/) (2026)
- [An Early Warning of Emerging Biosecurity Risks in Frontier LLMs](https://mlsanity.com/paper/2607.18056/) (2026)
- [Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration](https://mlsanity.com/paper/2609.16204/) (2026)
- [A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models](https://mlsanity.com/paper/2607.12200/) (2026)
- [Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance](https://mlsanity.com/paper/2609.16213/) (2026)

## Abstract (arXiv)

Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable humans to perform better than with internet-only resources. This uncertainty is central to understanding both scientific acceleration and dual-use risk. We conducted a multi-model, multi-benchmark human uplift study comparing novices with LLM access versus internet-only access across eight biosecurity-relevant task sets. Participants worked on complex problems with ample time (up to 13 hours for the most involved tasks). We found that LLM access provided substantial uplift: novices with LLMs were 4.16 times more accurate than controls (95% CI [2.63, 6.87]). On four benchmarks with available expert baselines (internet-only), novices with LLMs outperformed experts on three of them. Perhaps surprisingly, standalone LLMs often exceeded LLM-assisted novices, indicating that users were not eliciting the strongest available contributions from the LLMs. Most participants (89.6%) reported little difficulty obtaining dual-use-relevant information despite safeguards. Overall, LLMs substantially uplift novices on biological tasks previously reserved for trained practitioners, underscoring the need for sustained, interactive uplift evaluations alongside traditional benchmarks.