A ten-strategy taxonomy of distractor-generation strategies grounded in learning-science literature and observed LLM reasoning¶
Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 causal),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
The article introduces a taxonomy of ten distractor-generation strategies, "grounded in learning-science literature and empirical observations of LLMs’ reasoning traces", spanning task understanding (INTER, CORR), candidate construction (LINK, ERR_DESC, ERR_SIM, INST), quality control and selection (PLAUS, DISCR, CURATE), and cross-cutting reconsideration (RECON). It was built by merging expert-practice strategies from the literature with strategies extracted via manual open coding of LLM traces, and is applied to annotate 885 reasoning traces span by span.
Accounts¶
- A ten-strategy taxonomy of distractor-generation strategies grounded in learning-science literature and observed LLM reasoning: The article introduces a taxonomy of ten distractor-generation strategies, "grounded in learning-science literature and empirical observations of LLMs’ reasoning traces", spanning task understanding (INTER, CORR), candidate construction (LINK, ERR_DESC, ERR_SIM, INST), quality control and selection (PLAUS, DISCR, CURATE), and cross-cutting reconsideration (RECON). It was built by merging expert-practice strategies from the literature with strategies extracted via manual open coding of LLM traces, and is applied to annotate 885 reasoning traces span by span. (Yanick Zengaffinen et al. (2026))
Claims¶
- LLM distractor-generation strategies differ by domain: error description and simulation dominate on math while conceptual linking and discriminability checks dominate on science [+M]
- On the misconception-annotated math dataset, LLMs predominantly follow a solve-first, error-injection process aligned with misconception-based distractor design [+M]
Related Research Methods¶
-
Key Sources¶
- Yanick Zengaffinen, Andreas Opedal, Donya Rooein, Kv Aditya Srivatsa, Shashank Sonkar, Mrinmaya Sachan. (2026). Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation for Multiple-Choice Questions. https://arxiv.org/abs/2603.15547
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
a-ten-strategy-taxonomy-of-distractor-generation-strategies-grounded-in-learning-science-l |
title |
A ten-strategy taxonomy of distractor-generation strategies grounded in learning-science literature and observed LLM reasoning |
description |
The article introduces a taxonomy of ten distractor-generation strategies, "grounded in learning-science literature and empirical observations of LLMs’ reasoning traces", spanning task understanding (INTER, CORR), candidate construction (LINK, ERR_DESC, ERR_SIM, INST), quality control and selection |
status |
review |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.