Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning
Authors: Jan Net'ik, Patr'icia Martinkov'a
Summary
arXiv:2605. 16991v1 Announce Type: new Abstract: Response-free item difficulty modelling promises to reduce reliance on response-based calibration but is intrinsically difficult on reading-comprehension multiple-choice items, where difficulty depends on inferential demands across wording components.
Relevance
Read next because Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, text, word, under, eval, line, rate, test. Source: arxiv cs.CL (NLP).
Abstract
arXiv:2605.16991v1 Announce Type: new Abstract: Response-free item difficulty modelling promises to reduce reliance on response-based calibration but is intrinsically difficult on reading-comprehension multiple-choice items, where difficulty depends on inferential demands across wording components. Whereas most existing approaches extract item-text features and pass them to a separate statistical or machine-learning model, we fine-tune transformer encoders end-to-end on the item wording, eliminating the manual feature engineering and preprocessing that discards information. Moreover, two extensions to this joint-encoding approach are proposed: a component-wise variant that encodes wording components separately through a shared encoder, and a multi-task variant that retains joint encoding and adds an auxiliary multiple-choice question answering objective on the shared encoder. Each method is evaluated under a Monte Carlo subsampling design at three training-set sizes on a held-out test set. We find that joint encoding is a viable end-to-end alternative to feature-engineering pipelines; while the component-wise variant shows no detectable benefit, consistent with self-attention already harvesting the cross-component signal, the multi-task variant delivers significant paired improvements in the smallest-sample regime. Transformer fine-tuning, especially if regularised by a suitable auxiliary task, recovers a substantial share of the wording-derivable signal at training-set sizes typical of applied measurement. The framework provides a customisable interface for psychometrically motivated extensions.