# Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models

arXiv: https://arxiv.org/abs/2606.20959 · HTML: https://mlsanity.com/paper/2606.20959/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2407.17023/) (2024)
- [Time is Encoded in the Weights of Finetuned Language Models](https://mlsanity.com/paper/2312.13401/) (2023)
- [Taming Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2503.10996/) (2025)
- [Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models](https://mlsanity.com/paper/2311.08106/) (2023)
- [Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning](https://mlsanity.com/paper/2311.09821/) (2023)
- [UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization](https://mlsanity.com/paper/2407.03525/) (2024)
- [Question Answering as Programming for Solving Time-Sensitive Questions](https://mlsanity.com/paper/2305.14221/) (2023)
- [Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time](https://mlsanity.com/paper/2409.13338/) (2024)
- [Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation](https://mlsanity.com/paper/2605.09253/) (2026)
- [MuLan: A Study of Fact Mutability in Language Models](https://mlsanity.com/paper/2404.03036/) (2024)
- [Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time](https://mlsanity.com/paper/2512.04748/) (2025)
- [Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention](https://mlsanity.com/paper/2603.27187/) (2026)
- [TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints](https://mlsanity.com/paper/2605.13414/) (2026)
- [Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models](https://mlsanity.com/paper/2601.09445/) (2026)
- [Temporal Alignment of Time Sensitive Facts with Activation Engineering](https://mlsanity.com/paper/2505.14158/) (2025)
- [UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers](https://mlsanity.com/paper/2602.02952/) (2026)
- [Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN](https://mlsanity.com/paper/2603.15892/) (2026)

## Built on by (most cited first, 2 of 2)

- [Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains](https://mlsanity.com/paper/2608.03219/) (2026)
- [New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models](https://mlsanity.com/paper/2609.11022/) (2026)

## Abstract (arXiv)

Language models may encode both outdated facts and their newer replacements. We introduce Parametric Temporal Conflict (PTC), where the newer fact is present and recoverable, but the default forward pass prefers the outdated one. We release a deterministically verified benchmark of 8,746 Wikidata position-holder transitions and evaluate four open-weight language models across three families. A date-prefix prompt recovers the newer fact in 61-81% of PTC cases. Activation patching flips predictions in 72-85% of cases and localizes the preference to model-specific upper-layer regions. Residual-stream steering outperforms norm-matched random directions, indicating direction-specific representations. These results show that PTC reflects a localized representational preference rather than missing knowledge. Recovery is measured on oracle-identified conflicts because automatic detection remains unreliable. We release the benchmark, code, and statistics.