TCC-RAG: Temporal Causal Chain-Guided RAG for Temporal Knowledge Graph Question Answering
cs.CL
Submitted: 2026-10-28
Updated: 2026-11-18
Comments: 14 pages, 6 figures, ICDE2027 Research Track
License: http://creativecommons.org/licenses/by/4.0/
The gist: Recent advances in large language models (LLMs) have spurred growing interest in temporal knowledge graph question answering (TKGQA).
Terminology
Abstract
Recent advances in large language models (LLMs) have spurred growing interest in temporal knowledge graph question answering (TKGQA). Most existing methods rely on semantic retrieval augmented generation (RAG), which suffers from fundamental limitations in complex temporal reasoning. On the one hand, semantic-based RAG methods struggle to capture the multi-hop causal knowledge required for complex temporal reasoning. On the other hand, these methods introduce excessive redundant knowledge, trapping LLMs in spurious reasoning chains that potentially result in erroneous answers. To address these problems, we propose a Temporal Causal Chain-guided RAG (TCC-RAG) to retrieve a concise yet sufficient set of causal knowledge to support complex temporal reasoning. Specifically, we reformulate the temporal knowledge graph into a multi-view causal cue graph, with causal cues inducing connections that explicitly encode temporal evolution and causal dynamics. Based on the causal cue graph, we construct a query-specific temporal causal chain to guide the retrieval process, enabling the model to focus on a concise set of causally relevant knowledge. Finally, we introduce a causal evidence filter to refine the retrieved knowledge, ensuring its causal consistency with the underlying temporal logic of the query. Experiments show that TCC-RAG achieves substantial performance gains of 10.72% and 8.40% on two TKGQA benchmarks, and delivers a remarkable 62.97% improvement for multi-step temporal reasoning.
Sources
- GPT-4 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Temporal Knowledge Graph Question Answering: A Survey
- It's High Time: A Survey of Temporal Question Answering
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Question Answering Over Temporal Knowledge Graphs
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- The Llama 3 Herd of Models
- DeepSeek-V3 Technical Report
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data