Llama-Polya: Instruction Tuning for Large Language Model based on Polya's Problem-solving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915791152087040 |
|---|---|
| author | Lee, Unggi Jeong, Yeil Lee, Chohui Byun, Gyuri Lee, Yunseo Kang, Minji Jeon, Minji |
| author_facet | Lee, Unggi Jeong, Yeil Lee, Chohui Byun, Gyuri Lee, Yunseo Kang, Minji Jeon, Minji |
| contents | This paper introduces Llama-Polya, an instruction-tuned large language model that integrates Polya's four-step problem-solving framework into its dialogue structure to support mathematical reasoning. Mathematical problem-solving is central to students' success in mathematics education, yet many learners struggle to plan, justify, and verify their solutions. Although large language models (LLMs) show promise as intelligent tutors, they often lack structured pedagogical alignment grounded in established learning theories.
To address this gap, we operationalize Polya's problem-solving framework within an instruction-tuned LLM to promote metacognitive engagement and examine the effects of pedagogy-aligned fine-tuning compared to domain-only and general-purpose instruction tuning. Built on the Llama-3.1-8B architecture, Llama-Polya was fine-tuned on synthetic math problem-solving data derived from GSM8K, structured according to Polya's four stages. We developed and evaluated multiple variants-general-purpose instruct, math-domain metamath, pedagogy-aligned polya-v2, and sequential metamath+polya-v2-using both quantitative accuracy metrics and qualitative pedagogical assessments.
Results indicate that models tuned with Polya's framework and domain-specific data produced more balanced reasoning-stage distributions and fewer premature answers. Expert evaluators also observed improved pedagogical coherence and metacognitive prompting, although limitations in personalization and mathematical rigor remained. These findings suggest that pedagogy-grounded instruction tuning can enhance educational alignment and reasoning transparency in LLM-based tutoring systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Llama-Polya: Instruction Tuning for Large Language Model based on Polya's Problem-solving Lee, Unggi Jeong, Yeil Lee, Chohui Byun, Gyuri Lee, Yunseo Kang, Minji Jeon, Minji Computers and Society This paper introduces Llama-Polya, an instruction-tuned large language model that integrates Polya's four-step problem-solving framework into its dialogue structure to support mathematical reasoning. Mathematical problem-solving is central to students' success in mathematics education, yet many learners struggle to plan, justify, and verify their solutions. Although large language models (LLMs) show promise as intelligent tutors, they often lack structured pedagogical alignment grounded in established learning theories. To address this gap, we operationalize Polya's problem-solving framework within an instruction-tuned LLM to promote metacognitive engagement and examine the effects of pedagogy-aligned fine-tuning compared to domain-only and general-purpose instruction tuning. Built on the Llama-3.1-8B architecture, Llama-Polya was fine-tuned on synthetic math problem-solving data derived from GSM8K, structured according to Polya's four stages. We developed and evaluated multiple variants-general-purpose instruct, math-domain metamath, pedagogy-aligned polya-v2, and sequential metamath+polya-v2-using both quantitative accuracy metrics and qualitative pedagogical assessments. Results indicate that models tuned with Polya's framework and domain-specific data produced more balanced reasoning-stage distributions and fewer premature answers. Expert evaluators also observed improved pedagogical coherence and metacognitive prompting, although limitations in personalization and mathematical rigor remained. These findings suggest that pedagogy-grounded instruction tuning can enhance educational alignment and reasoning transparency in LLM-based tutoring systems. |
| title | Llama-Polya: Instruction Tuning for Large Language Model based on Polya's Problem-solving |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2602.10597 |