Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN

• URL: http://arxiv.org/abs/2603.15892v1
• Date: Mon, 16 Mar 2026 20:37:17 GMT
• Title: Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN
• Abstract summary: Two recent studies report opposite conclusions on whether external context can effectively resolve temporal conflicts.<n>We reproduce experiments from both benchmarks and investigate the source of their disagreement.<n>Our results highlight how dataset design, evaluation metrics, and model size shape LLM behaviour in presence of temporal knowledge conflicts.
• Score: 19.373782553647597
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) often struggle with temporal fact conflicts due to outdated or evolving information in their training data. Two recent studies with accompanying datasets report opposite conclusions on whether external context can effectively resolve such conflicts. DYNAMICQA evaluates how effective external context is in shifting the model's output distribution, finding that temporal facts are more resistant to change. In contrast, MULAN examines how often external context changes memorised facts, concluding that temporal facts are easier to update. In this reproducibility paper, we first reproduce experiments from both benchmarks. We then reproduce the experiments of each study on the dataset of the other to investigate the source of their disagreement. To enable direct comparison of findings, we standardise both datasets to align with the evaluation settings of each study. Importantly, using an LLM, we synthetically generate realistic natural language contexts to replace MULAN's programmatically constructed statements when reproducing the findings of DYNAMICQA. Our analysis reveals strong dataset dependence: MULAN's findings generalise under both methodological frameworks, whereas applying MULAN's evaluation to DYNAMICQA yields mixed outcomes. Finally, while the original studies only considered 7B LLMs, we reproduce these experiments across LLMs of varying sizes, revealing how model size influences the encoding and updating of temporal facts. Our results highlight how dataset design, evaluation metrics, and model size shape LLM behaviour in the presence of temporal knowledge conflicts.

Related papers

• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Positional Biases Shift as Inputs Approach Context Window Limits [57.00239097102958]
  The LiM effect is strongest when inputs occupy up to 50% of a model's context window.<n>We observe a distance-based bias, where model performance is better when relevant information is closer to the end of the input.
  arXiv  Detail & Related papers  (2025-08-10T20:40:24Z)
• RelationalFactQA: A Benchmark for Evaluating Tabular Fact Retrieval from Large Language Models [9.211266032947497]
  We demonstrate that fact retrieval is substantially more difficult than isolated point-wise queries.<n>Our experiments reveal that even stateofthe-art LLMs struggle significantly, not exceeding 25% factual accuracy.<n>These findings underscore limitations in current LLMs' ability to synthesize structured factual knowledge.
  arXiv  Detail & Related papers  (2025-05-27T16:33:38Z)
• Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling [56.26834106704781]
  Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs)<n>We provide evidence supporting the presence of LLMs' internal compass that dictate the correctness of factual recall at the time of generation.<n>Scaling experiments across model sizes and training dynamics highlight that self-awareness emerges rapidly during training and peaks in intermediate layers.
  arXiv  Detail & Related papers  (2025-05-27T16:24:02Z)
• Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs [48.202202256201815]
  Factual hallucinations are a major challenge for Large Language Models (LLMs)<n>They undermine reliability and user trust by generating inaccurate or fabricated content.<n>Recent studies suggest that when generating false statements, the internal states of LLMs encode information about truthfulness.
  arXiv  Detail & Related papers  (2025-05-22T11:00:53Z)
• SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data [15.366930934639838]
  We propose SALAD, a novel approach to enhance model robustness and generalization.<n>Our method generates structure-aware and counterfactually augmented data for contrastive learning.<n>We validate our approach through experiments on three tasks: Sentiment Classification, Sexism Detection, and Natural Language Inference.
  arXiv  Detail & Related papers  (2025-04-16T15:40:10Z)
• ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models [75.05436691700572]
  We introduce ExpliCa, a new dataset for evaluating Large Language Models (LLMs) in explicit causal reasoning.<n>We tested seven commercial and open-source LLMs on ExpliCa through prompting and perplexity-based metrics.<n>Surprisingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events.
  arXiv  Detail & Related papers  (2025-02-21T14:23:14Z)
• Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning [20.066249913943405]
  Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors. We introduce novel synthetic datasets specifically designed to assess LLM temporal reasoning abilities in various scenarios. Our findings provide valuable insights into the strengths and weaknesses of current LLMs in temporal reasoning tasks.
  arXiv  Detail & Related papers  (2024-06-13T14:31:19Z)
• Evaluating Consistency and Reasoning Capabilities of Large Language Models [0.0]
  Large Language Models (LLMs) are extensively used today across various sectors, including academia, research, business, and finance. Despite their widespread adoption, these models often produce incorrect and misleading information, exhibiting a tendency to hallucinate. This paper aims to evaluate and compare the consistency and reasoning capabilities of both public and proprietary LLMs.
  arXiv  Detail & Related papers  (2024-04-25T10:03:14Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.