# TraceBack: Multi-Agent Decomposition for Fine-Grained Table Attribution

arXiv: https://arxiv.org/abs/2602.13059 · HTML: https://mlsanity.com/paper/2602.13059/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [Automatic Evaluation of Attribution by Large Language Models](https://mlsanity.com/paper/2305.06311/) (2023)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [A Retrospective Analysis of the Fake News Challenge Stance Detection Task](https://mlsanity.com/paper/1806.05180/) (2018)
- [AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry](https://mlsanity.com/paper/2106.12944/) (2021)
- [H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables](https://mlsanity.com/paper/2407.05952/) (2024)

## Abstract (arXiv)

Question answering (QA) over structured tables requires not only accurate answers but also transparency about which cells support them. Existing table QA systems rarely provide fine-grained attribution, so even correct answers often lack verifiable grounding, limiting trust in high-stakes settings. We address this with TraceBack, a modular multi-agent framework for scalable, cell-level attribution in single-table QA. TraceBack prunes tables to relevant rows and columns, decomposes questions into semantically coherent sub-questions, and aligns each answer span with its supporting cells, capturing both explicit and implicit evidence used in intermediate reasoning steps. To enable systematic evaluation, we release CITEBench, a benchmark with phrase-to-cell annotations drawn from ToTTo, FetaQA, and AITQA. We further propose FairScore, a reference-less metric that compares atomic facts derived from predicted cells and answers to estimate attribution precision and recall without human cell labels. Experiments show that TraceBack substantially outperforms strong baselines across datasets and granularities, while FairScore closely tracks human judgments and preserves relative method rankings, supporting interpretable and scalable evaluation of table-based QA.