ACL Findings2026
Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
Shengbo Gong, Xianfeng Tang, Qi He, Carl Yang, Wei Jin
Abstract
Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency. Multi-round RAG approaches achieve strong reasoning but incur excessive LLM calls and token costs, while Graph RAG methods suffer from computationally expensive, error-prone graph construction and retrieval redundancy. To address these challenges, we propose T 2 RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets. T 2 RAG leverages an LLM to decompose questions into searchable triplets with placeholders, which it then iteratively resolves by retrieving evidence from the triplet database. Empirical results show that T 2 RAG significantly outperforms state-of-the-art multiround and Graph RAG methods, achieving an average performance gain of up to 11% across six datasets while reducing retrieval costs by up to 45%. Our code is available at https:// anonymous.4open.science/r/T2RAG-DF75. 1 26282 (a) Multi-round RAG (b) Graph RAG (c) Triplet-driven Thinking RAG (Ours)
Question: Which film has the director born earlier, God's Gift To Women or Aldri Annet Enn Brak? I need to find the birth years of the directors of both films: Michael Curtiz for "God's Gift to Women" and Edith Carlmar for "Aldri annet enn bråk....
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- NuggetIndex: Governed Atomic Retrieval for Maintainable RAG cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Cited by top-tier papers2
Builds on33
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTOmar Khattab, Matei ZahariaSIGIR 2020 · 1,246 citations
- Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui PanICLR 2024 · 499 citations
- RAPTOR: Recursive Abstractive Processing for Tree-Organized RetrievalParth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna et al.ICLR 2024 · 460 citations
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga et al.NeurIPS 2024 · 395 citations
Related papers
- AED-RAG: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble DecodingJunzhe Zhou, Fulin Lin, Tairan Cheng, Shaowen Chen et al.ACL Findings 2026
- TH-RAG : Topic-Based Hierarchical Knowledge Graphs for Robust Multi-hop Reasoning in Graph-based RAG SystemsJungHyoun Kim, Soohyeong Kim, Seok Jun Hwang, Jeonghyeon Park et al.ACL 2026
- PropRAG: Guiding Retrieval with Beam Search over Proposition PathsJingjin Wang, Jiawei HanEMNLP 2025
- LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale CorporaLuyao Zhuang, Shengyuan Chen, Yilin Xiao, Huachi Zhou et al.ICLR 2026 · 54 citations
- TC-RAG: Turing-Complete RAG's Case study on Medical LLM SystemsXinke Jiang, Yue Fang, Rihong Qiu, Haoyu Zhang et al.ACL 2025
