Papers › DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models

24 Jul 2024arXiv:2407.17023archive 2025-07-28

Sara Vera Marjanović, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, Isabelle Augenstein

Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. However, conflicting knowledge can be present in the LM's parameters, termed intra-memory conflict, which can affect a model's propensity to accept contextual knowledge. To study the effect of intra-memory conflict on an LM's ability to accept relevant context, we utilize two knowledge conflict measures and a novel dataset containing inherently conflicting data, DynamicQA. This dataset includes facts with a temporal dynamic nature where facts can change over time and disputable dynamic facts, which can change depending on the viewpoint. DynamicQA is the first to include real-world knowledge conflicts and provide context to study the link between the different types of knowledge conflicts. We also evaluate several measures on their ability to reflect the presence of intra-memory conflict: semantic entropy and a novel coherent persuasion score. With our extensive experiments, we verify that LMs exhibit a greater degree of intra-memory conflict with dynamic facts compared to facts that have a single truth value. Furthermore, we reveal that facts with intra-memory conflict are harder to update with context, suggesting that retrieval-augmented generation will struggle with the most commonly adapted facts.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.17023")

Code

Syntology Ran 6 of 9 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

copenlu/dynamicqa officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 6 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6ran
3unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from copenlu/dynamicqa. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

clean_str copenlu/dynamicqa/final_code/get_stubborn_persuaded_instances.py official repository ran fingerprinted no licence file found · pointer only · 6be46e1c5df4f04d · report
encode_and_format_dataset copenlu/dynamicqa/final_code/generation_utils.py official repository ran no licence file found · pointer only · 48fc594b35bcd992 · report
get_log_likelihood_variance copenlu/dynamicqa/final_code/compute_confidence_measure.py official repository ran fingerprinted no licence file found · pointer only · 707426419c228afb · report
get_mutual_information copenlu/dynamicqa/final_code/compute_confidence_measure.py official repository ran fingerprinted no licence file found · pointer only · 6968b47de84cea75 · report
get_overall_log_likelihoods copenlu/dynamicqa/final_code/compute_confidence_measure.py official repository ran no licence file found · pointer only · d76f91e497146830 · report
load_reference copenlu/dynamicqa/final_code/get_stubborn_persuaded_instances.py official repository ran no licence file found · pointer only · 210a13606bd58095 · report
encode_as_chat copenlu/dynamicqa/final_code/generation_utils.py official repository unverified no licence file found · pointer only · 14f690a9375b0682 · report
find_stubborn_example copenlu/dynamicqa/final_code/get_stubborn_persuaded_instances.py official repository unverified no licence file found · pointer only · 08e647c1eaccd4a0 · report
load_model copenlu/dynamicqa/final_code/generation_utils.py official repository unverified no licence file found · pointer only · 60b894ff063b237b · report

Tasks

Retrieval-augmented GenerationWorld Knowledge

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections