Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909839122235392 |
|---|---|
| author | Ding, Zifeng Huang, Shenyang Cao, Zeyu Kondrup, Emma Yang, Zachary Huang, Xingyue Sui, Yuan Yuan, Zhangdie Zhu, Yuqicheng Hu, Xianglong He, Yuan Poursafaei, Farimah Bronstein, Michael Vlachos, Andreas |
| author_facet | Ding, Zifeng Huang, Shenyang Cao, Zeyu Kondrup, Emma Yang, Zachary Huang, Xingyue Sui, Yuan Yuan, Zhangdie Zhu, Yuqicheng Hu, Xianglong He, Yuan Poursafaei, Farimah Bronstein, Michael Vlachos, Andreas |
| contents | Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve strong performance but lack explainability and cannot be applied to unseen graphs without retraining. Recent studies have begun to explore using large language models (LLMs) for graph reasoning, but most of them are constrained to static graphs or small synthetic TGs and lack the evaluation of the quality of reasoning traces generated by LLMs. In this work, we present Reasoning-Enhanced Learning for Temporal Graphs (ReaL-TG), a reinforcement learning framework that fine-tunes LLMs to perform explainable link forecasting on real-world TGs. ReaL-TG uses outcome-based reward to encourage models to self-explore reasoning strategies from graph structure and to produce explanations that directly justify their predictions. To enable evaluation on LLM-generated reasoning traces, we propose a new evaluation protocol combining ranking metrics with an LLM-as-a-Judge system that assesses both the quality of reasoning and the impact of hallucinations. Experiments with ReaL-TG-4B, obtained by fine-tuning Qwen3-4B under our framework, show that it outperforms much larger frontier LLMs, including GPT-5 mini, on ranking metrics, while producing high-quality explanations confirmed by both the LLM judge and human evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning Ding, Zifeng Huang, Shenyang Cao, Zeyu Kondrup, Emma Yang, Zachary Huang, Xingyue Sui, Yuan Yuan, Zhangdie Zhu, Yuqicheng Hu, Xianglong He, Yuan Poursafaei, Farimah Bronstein, Michael Vlachos, Andreas Artificial Intelligence Computation and Language Machine Learning Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve strong performance but lack explainability and cannot be applied to unseen graphs without retraining. Recent studies have begun to explore using large language models (LLMs) for graph reasoning, but most of them are constrained to static graphs or small synthetic TGs and lack the evaluation of the quality of reasoning traces generated by LLMs. In this work, we present Reasoning-Enhanced Learning for Temporal Graphs (ReaL-TG), a reinforcement learning framework that fine-tunes LLMs to perform explainable link forecasting on real-world TGs. ReaL-TG uses outcome-based reward to encourage models to self-explore reasoning strategies from graph structure and to produce explanations that directly justify their predictions. To enable evaluation on LLM-generated reasoning traces, we propose a new evaluation protocol combining ranking metrics with an LLM-as-a-Judge system that assesses both the quality of reasoning and the impact of hallucinations. Experiments with ReaL-TG-4B, obtained by fine-tuning Qwen3-4B under our framework, show that it outperforms much larger frontier LLMs, including GPT-5 mini, on ranking metrics, while producing high-quality explanations confirmed by both the LLM judge and human evaluation. |
| title | Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.00975 |