STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911199841484800 |
|---|---|
| author | Lee, Kyumin Jeon, Minjin Jang, Sanghwan Yu, Hwanjo |
| author_facet | Lee, Kyumin Jeon, Minjin Jang, Sanghwan Yu, Hwanjo |
| contents | Answering complex real-world questions requires step-by-step retrieval and integration of relevant information to generate well-grounded responses. However, existing knowledge distillation methods overlook the need for different reasoning abilities at different steps, hindering transfer in multi-step retrieval-augmented frameworks. To address this, we propose Stepwise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models (StepER). StepER employs step-wise supervision to align with evolving information and reasoning demands across stages. Additionally, it incorporates difficulty-aware training to progressively optimize learning by prioritizing suitable steps. Our method is adaptable to various multi-step retrieval-augmented language models, including those that use retrieval queries for reasoning paths or decomposed questions. Extensive experiments show that StepER outperforms prior methods on multi-hop QA benchmarks, with an 8B model achieving performance comparable to a 70B teacher model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07923 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models Lee, Kyumin Jeon, Minjin Jang, Sanghwan Yu, Hwanjo Computation and Language Artificial Intelligence Answering complex real-world questions requires step-by-step retrieval and integration of relevant information to generate well-grounded responses. However, existing knowledge distillation methods overlook the need for different reasoning abilities at different steps, hindering transfer in multi-step retrieval-augmented frameworks. To address this, we propose Stepwise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models (StepER). StepER employs step-wise supervision to align with evolving information and reasoning demands across stages. Additionally, it incorporates difficulty-aware training to progressively optimize learning by prioritizing suitable steps. Our method is adaptable to various multi-step retrieval-augmented language models, including those that use retrieval queries for reasoning paths or decomposed questions. Extensive experiments show that StepER outperforms prior methods on multi-hop QA benchmarks, with an 8B model achieving performance comparable to a 70B teacher model. |
| title | STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.07923 |