cs.CLNov 13, 2026

LitArc-Bench: Disentangling Text-Specific Reader-Response Dynamics from Position and Lexical Affect

Authors: Mingming Su, Yushan Wei, Sen Song, Xinche Zhang

Organizations: Capital University of Economics and Business · Shanghai International Studies University · Tsinghua University

Abstract

When model predictions track an unfolding human affect trajectory, alignment may reflect narrative position, affective words, or text-specific reader-response dynamics. We introduce LitArc-Bench to separate these explanations: 39 Chinese-language literary excerpts segmented into seven checkpoints, with 430 questionnaires from 81 adults in two classroom groups (9,020 VAD ratings). We compare three future-blind model runs with leave-one-text-out position priors, lexical affect, and human-human references. Position alone reaches r = .470 for arousal, making raw alignment insufficient. Yet all six V/A transition advantages over a joint position-lexicon control have text-bootstrap intervals above zero. Cross-fitted models match the correct human text better than 38 mismatched texts in all nine model-dimension cells (p < .0001); a text-invariant negative control returns chance (p = 1). On human transitions at least 0.5 points against the position trend, models recover 69-76% of valence directions and 53-68% for arousal and dominance. Under crossed participant-text resampling, all nine identity intervals remain above zero; joint-control advantages are robust for valence and directional but less certain for arousal. High shape agreement still coexists with scale bias. LitArc-Bench identifies which components of literary reader response are recoverable beyond shallow explanations and why shape, calibration, and human variability require separate evaluation.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AI translation of literary texts is "fine", but readers still prefer human translations

    Jun 24, 2026Yves Ferstler, Adam Podoxin, Ty Brassington +5Machine TranslationMT Evaluation

  2. From annotation to reasoning: Culture in language models

    Sep 25, 2026Daniel Hershcovich, Alexander Conroy, Jens Bjerring-HansenCultural Knowledge in Language ModelsCross-Cultural Language Model Evaluation

  3. The LALA Benchmark: Evaluating Literary and Linguistic Analysis in LLMs

    Oct 25, 2026Michael Foster, Barbara McGillivray, Gard B. Jenset +7LLM EvaluationLanguage Model Post-Training