The full Special-R1 model raises persona-aware Fit from 6.75 to 8.40 and SPED-rubric Helpfulness from 0.720 to 0.768 over a non-disability-aware baseline¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? On a persona-augmented test set of 690 multi-turn dialogues, the full model (M7) raises persona-aware Fit from 6.75 (generic baseline) to 8.40 and SPED-rubric Helpfulness from 0.720 to 0.768. → Unggi Lee 2026

Evidence¶

Unggi Lee 2026¶

Unggi Lee, Jihoi Na, Yeil Jeong, Haeun Park, Yeonju Jang. (2026). Reinforcement Learning for Special Education: Aligning LLM Tutors to Diverse Learners through Disability-Adaptive Training. https://arxiv.org/abs/2605.30670 doi:10.48550/arxiv.2605.30670

q2 · i? · design · r2

Evaluation of seven trained tutor configurations on the SPED-Tutor-Mix conversational test set (N=690), with LLM-judge scores macro-averaged across disability types. The full model M7 leads the four-component Total at 2.911, "+0.064 over the runner-up" M6, and leads all four persona dimensions simultaneously.

"On a persona-augmented test set of 690 multi-turn dialogues, our full model raises persona-aware Fit from 6.75 (generic baseline) to 8.40 (+1.65) and SPED-rubric Helpfulness from 0.720 to 0.768"

Discussion¶

Related Claims¶

• Specific learning disability in mathematics is the weakest persona profile across all GRPO-trained models — related
• Prompt style is the largest driver of disability-aware Fit gains, and the Thinking Reward becomes effective only in combination with adaptive prompting — related
• SPED-adaptive prompting shifts tutor behavior toward We-Do scaffolding, naturalistic language support, and participation-affirming feedback across three codebooks — related
• Disability-aware training does not degrade out-of-domain educational knowledge on OpenLearnLM — related