Search papers, labs, and topics across Lattice.
The study introduces a "Bioalignment" metric to quantify LLMs' biases towards synthetic versus biological solutions across materials, energy, manufacturing, and algorithms, finding that most models favor synthetic approaches. They then fine-tuned Llama 3.2-3B-Instruct and Qwen2.5-3B-Instruct with a corpus of PMC articles emphasizing biological problem-solving, using QLoRA. This fine-tuning significantly increased the models' preference for biological solutions without degrading general capabilities, as measured by the Bioalignment metric.
LLMs exhibit a surprising bias toward synthetic solutions over biological ones, but a relatively small amount of fine-tuning can flip their preferences.
Large language models (LLMs) trained on internet-scale corpora can exhibit systematic biases that increase the probability of unwanted behavior. In this study, we examined potential biases towards synthetic vs. biological technological solutions across four domains (materials, energy, manufacturing, and algorithms). A sample of 5 frontier and 5 open-weight models were measured using 50 curated Bioalignment prompts with a Kelly criterion-inspired evaluation framework. According to this metric, most models were not bioaligned in that they exhibit biases in favor of synthetic (non-biological) solutions. We next examined if fine-tuning could increase the preferences of two open-weight models, Llama 3.2-3B-Instruct and Qwen2.5-3B-Instruct, for biological-based approaches. A curated corpus of ~22M tokens from 6,636 PMC articles emphasizing biological problem-solving was used first to fine-tune Llama 3B with a mixed corpus of continued training and instruction-formatted. This was then extended to Qwen 3B using instruction-formatted only. We found that QLoRA fine-tuning significantly increased the scoring of biological solutions for both models without degrading general capabilities (Holm-Bonferroni-corrected p<0.001 and p<0.01, respectively). This suggests that even a small amount of fine-tuning can change how models weigh the relative value of biological and bioinspired vs. synthetic approaches. Although this work focused on small open-weight LLMs, it may be extensible to much larger models and could be used to develop models that favor bio-based approaches. We release the benchmark, corpus, code, and adapter weights.
