# DiffIE: Diffusion-based Open Information Extraction

arXiv: https://arxiv.org/abs/2609.02315 · HTML: https://mlsanity.com/paper/2609.02315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 11 of 11)

- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Simple Guidance Mechanisms for Discrete Diffusion Models](https://mlsanity.com/paper/2412.10193/) (2024)
- [Neural Open Information Extraction](https://mlsanity.com/paper/1805.04270/) (2018)
- [Span Model for Open Information Extraction on Accurate Corpus](https://mlsanity.com/paper/1901.10879/) (2019)
- [WiRe57 : A Fine-Grained Benchmark for Open Information Extraction](https://mlsanity.com/paper/1809.08962/) (2018)
- [LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction](https://mlsanity.com/paper/2101.11177/) (2021)
- [BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation](https://mlsanity.com/paper/2109.06850/) (2021)
- [DetIE: Multilingual Open Information Extraction Inspired by Object Detection](https://mlsanity.com/paper/2206.12514/) (2022)
- [Efficient Data Learning for Open Information Extraction with Pre-trained Language Models](https://mlsanity.com/paper/2310.15021/) (2023)
- [Exploiting Duality in Open Information Extraction with Predicate Prompt](https://mlsanity.com/paper/2401.11107/) (2024)

## Abstract (arXiv)

A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction, which is efficient but couples the extraction budget to training. We introduce DIFFIE which instead treats the stochasticity of conditional discrete diffusion as the extraction mechanism itself: independent reverse-diffusion trajectories over per-token role tags produce a pool of candidate triplets, which are clustered under lenient matching and ranked to form the output. Both the pool size and the number of returned extractions are inference-time choices, decoupling the extraction budget from training and exposing test-time compute as a tunable axis. DIFFIE achieves the new state of the art in CaRB (1-1) both F1 and AUC, and outperforms the strongest rule-based system (ClausIE) in BenchIE; it also remains competitive in standard CaRB and WiRe57 evaluations, giving the best average score among systems that report all four benchmarks. Ablations show that uniform discrete diffusion outperforms absorbing state diffusion in our setting, and that a matched non-diffusion stochastic tagger does not reproduce its gains. Our results indicate that diffusion stochasticity is an effective mechanism for structured prediction tasks with multiple valid outputs.