Metraipolis › archive › dc_2ff322445bc9
Do LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness — arXiv:2610.26961
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.26961
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:09:13.253Z
- SHA-256 of the archived text
55b2d68bcf2da266ca559508fb4396b7faa63ea591df758a012df45dc99b9a55- Stable URL of this page
https://metraipolis.com/documento/dc_2ff322445bc9
How to cite
Do LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness — arXiv:2610.26961 — arXiv (en), https://arxiv.org/abs/2610.26961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ff322445bc9 (Metraipolis archive dc_2ff322445bc9, sha256 55b2d68bcf2da266ca559508fb4396b7faa63ea591df758a012df45dc99b9a55)
BibTeX
@misc{dc2ff322445bc9,
title = {Do LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness — arXiv:2610.26961},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.26961},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ff322445bc9; sha256 55b2d68bcf2da266ca559508fb4396b7faa63ea591df758a012df45dc99b9a55},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we investigate the issue of difference awareness in LLMs, defined as a model's ability to recognize and acknowledge meaningful differences between social groups in fairness decision-making. Previous studies have consistently shown that models perform poorly on such tasks, a finding commonly attributed to a lack of difference awareness. We propose an alternative account, which we term Fairness Heuristic Substitution: difference awareness is not necessarily absent, but the complex demand of simultaneously identifying relevant group differences and determining their implications for fairness decisions may lead models to substitute the simpler, more accessible equal-treatment heuristic, i.e., formal equality. Based on this hypothesis, we introduce TDD, a Two-stage Distinguish-Decide framework that explicitly decomposes fairness reasoning into first distinguishing contextually relevant group differences and then making the corresponding decision, thereby discouraging reliance on formal-equality shortcuts. (i) Across four benchmarks and ten models ranging from billions to trillions of parameters, TDD significantly outperforms one-stage baselines, even one strengthened through simulated test-set leakage. (ii) Combining TDD with neuron-level contrastive probing provides mechanistic evidence consistent with the Fairness Heuristic Substitution hypothesis by revealing two signatures of the formal-equality: a compact, locally coordinated representational structure and a pronounced activation bias under default reasoning. (iii) TDD's stage-wise decomposition uncovers overlooked failure modes in fairness reasoning, including heuristic displacement and misaligned stage dynamics. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Social and Information Networks (cs.SI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.26961 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-21T07:05:58.162Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).