# Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override

arXiv: https://arxiv.org/abs/2606.07555 · HTML: https://mlsanity.com/paper/2606.07555/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 24 of 24)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking](https://mlsanity.com/paper/2402.14811/) (2024)
- [Inspecting and Editing Knowledge Representations in Language Models](https://mlsanity.com/paper/2304.00740/) (2023)
- [Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2402.18154/) (2024)
- [Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering](https://mlsanity.com/paper/2410.15999/) (2024)
- [Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming](https://mlsanity.com/paper/2010.03010/) (2020)
- [Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals](https://mlsanity.com/paper/2402.11655/) (2024)
- [Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents](https://mlsanity.com/paper/2404.16032/) (2024)
- [Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict](https://mlsanity.com/paper/2506.06485/) (2025)
- [The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation](https://mlsanity.com/paper/2604.23750/) (2026)
- [When Models Ignore Definitions: Measuring Semantic Override Hallucinations in LLM Reasoning](https://mlsanity.com/paper/2602.17520/) (2026)

## Abstract (arXiv)

Local definitions can assign a familiar word a temporary meaning while its usual associations remain useful elsewhere. We measure interference from those associations with a matched Stroop-style paradigm. A conflict prompt defines doctor as forest and compares forest with the familiar associate hospital. A neutral control replaces doctor with a semantically weak word in both the definition and query while keeping forest and hospital fixed. All 11 model-level means are positive. Aggregate means are also positive for all four conflict families and prompt formats. When no redefinition is present, a stronger preference for the familiar distractor predicts more interference in arbitrary-semantic, polysemy/entity, and domain-definition remappings, while the antonym slope is null. Separately, we patch neutral-control activations into antonym prompts in five 1B-2B models. Patching the defined word, the target word in the definition, and the later query word together restores almost all of the target-minus-distractor margin lost in conflict (normalized recovery R in [0.92,1.06]). Replacing only that target-word activation with a donor from another item reduces recovery in every tested case. Those donor patches also lower the distractor logit, while the contextual target falls much more than under the same-item patch that restores the margin.