Metraipolis › archive › dc_fb6a9e64fb99
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness — arXiv:2610.42054
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.42054
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:13:31.424Z
- SHA-256 of the archived text
91ba7415db4599cc5bafc234b622d20376c76add5e3b0f2f5ba66e03e291854f- Stable URL of this page
https://metraipolis.com/documento/dc_fb6a9e64fb99
How to cite
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness — arXiv:2610.42054 — arXiv (en), https://arxiv.org/abs/2610.42054 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb6a9e64fb99 (Metraipolis archive dc_fb6a9e64fb99, sha256 91ba7415db4599cc5bafc234b622d20376c76add5e3b0f2f5ba66e03e291854f)
BibTeX
@misc{dcfb6a9e64fb99,
title = {CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness — arXiv:2610.42054},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.42054},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb6a9e64fb99; sha256 91ba7415db4599cc5bafc234b622d20376c76add5e3b0f2f5ba66e03e291854f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42054. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correctness, which does not guarantee that the CoT causally contributes to the final answer. Without this connection, outcome rewards may fail to reinforce high-quality reasoning. Existing causality metrics assess CoT causality by perturbing the CoT, such as deleting reasoning steps or injecting errors, and measuring changes in the final answer. However, these perturbations inevitably alter information in each step. Consequently, high causality scores may reflect sensitivity to information changes introduced by perturbation rather than true causality. Such confounding effects further induce undesirable reasoning behaviors when these metrics are used as training rewards, including generating less informative CoTs and reducing exploration and self-correction. To address this problem, we propose CRoS (Causality Reward on Scrambled CoTs), a novel CoT causality metric that perturbs the order of reasoning steps without altering content, thereby preserving information within each step. On Reasoning Gym with Gemma-3-4B, CRoS outperforms existing causality and outcome rewards in out-of-domain accuracy, CoT quality, and CoT faithfulness. Specifically, CRoS achieves 46.8% accuracy on five unseen logic and games datasets, outperforming the strongest baseline (43.8%). It also achieves better CoT quality, consistently outperforming baselines in CoT-Pass@K from K=1 to 128, averaging 43.4% vs. 41.4%. For CoT faithfulness, CRoS achieves a hint acknowledgment score of 34.0% vs. 20.2%. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.42054 — 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 2026-11-03T07:09:31.893Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).