# What's in a Name? Morphological Shortcuts by LLMs in Pharmacology

arXiv: https://arxiv.org/abs/2606.05616 · HTML: https://mlsanity.com/paper/2606.05616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 13 of 13)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [CREPE: Open-Domain Question Answering with False Presuppositions](https://mlsanity.com/paper/2211.17257/) (2022)
- [(QA)2: Question Answering with Questionable Assumptions](https://mlsanity.com/paper/2212.10003/) (2022)
- [MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models](https://mlsanity.com/paper/2409.19492/) (2024)
- [Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks](https://mlsanity.com/paper/2406.12066/) (2024)
- [Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions](https://mlsanity.com/paper/2504.11373/) (2025)
- [A Comprehensive Study of Gender Bias in Chemical Named Entity Recognition Models](https://mlsanity.com/paper/2212.12799/) (2022)
- [Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence](https://mlsanity.com/paper/2601.11886/) (2026)
- [Community size rather than grammatical complexity better predicts Large Language Model accuracy in a novel Wug Test](https://mlsanity.com/paper/2510.12463/) (2025)

## Abstract (arXiv)

The morphological form of a word can often give cues to its meaning, but purely relying on these mappings can lead to overgeneralization in high-stakes domains. In the medical domain, for instance, LLMs can confidently reason about fictitious drugs from their affixes alone (e.g., wugcillin) and generate plausible-looking clinical content. We present a behavioral and mechanistic study of LLM "affix heuristics" in pharmacology. Using fictitious drug names built from real affixes, we show that affix signals alone elicit class-level pharmacological responses. We introduce a framework for identifying whether a model's drug semantics are driven mainly by the affix, the stem, or the drug name as a whole. Applied across 653 drugs, our framework reveals that models often induce drug meaning primarily through affix cues, yet rarely explicitly indicate this reliance, and sometimes incorrectly conflate properties among affix-sharing drugs. Activation patching across models further localizes this behavior to early-mid layers. These findings show that morphological shortcuts pose a subtle but measurable risk to safety.