# The Temporal Tug-of-War: Visualizing and Detecting RAG Conflicts in Diffusion Models via Trajectory Variance

arXiv: https://arxiv.org/abs/2609.31684 · HTML: https://mlsanity.com/paper/2609.31684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [Retrieval-Augmented Generation with Conflicting Evidence](https://mlsanity.com/paper/2504.13079/) (2025)
- [CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models](https://mlsanity.com/paper/2508.17670/) (2025)
- [TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs](https://mlsanity.com/paper/2602.08048/) (2026)
- [ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation](https://mlsanity.com/paper/2605.17301/) (2026)
- [Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models](https://mlsanity.com/paper/2601.11342/) (2026)
- [OSCAR: Orchestrated Self-verification and Cross-path Refinement](https://mlsanity.com/paper/2604.01624/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when retrieved context contradicts parametric knowledge, the iterative denoising process becomes a visible battleground between competing knowledge sources. We identify temporal semantic divergence as an observable for detecting these conflicts and introduce the Trajectory Variance Score (TVS), a simple and interpretable measure of this divergence. TVS computes the mean pairwise cosine distance of answer embeddings across independent stochastic denoising trajectories, capturing the temporal tug of war between parametric and contextual attractors. Requiring as few as two parallel inference runs, TVS is computationally lightweight. Across four diverse datasets (Synthetic, SciQ, PopQA, and CounterFact), a simple Logistic Regression classifier using TVS achieves 70.10% accuracy and 0.7647 AUROC on LLaDA. On Dream 7B, increasing the number of trajectories from two to five improves accuracy from 63.91% to 69.62%. More complex sequential models provide only marginal improvements over the linear classifier. Evaluation across LLaDA and Dream 7B demonstrates that conflict-induced trajectory dynamics and their key properties transfer across distinct diffusion architectures.