MétaCan
Menu
Back to cohort

Impact of Co-occurrence on Factual Knowledge of Large Language Models

2023· article· en· W4389519983 on OpenAlexaff
Cheongwoong Kang, Jaesik Choi

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsKootenay Association for Science & Technology
FundersInstitute for Information and Communications Technology PromotionMinistry of Science and ICT, South KoreaKorea Advanced Institute of Science and Technology
KeywordsComputer scienceSubject (documents)RecallObject (grammar)Set (abstract data type)Natural language processingArtificial intelligenceCognitive psychologyMachine learningPsychologyWorld Wide WebProgramming language

Abstract

fetched live from OpenAlex

Large language models (LLMs) often make factually incorrect responses despite their success in various applications.In this paper, we hypothesize that relying heavily on simple cooccurrence statistics of the pre-training corpora is one of the main factors that cause factual errors.Our results reveal that LLMs are vulnerable to the co-occurrence bias, defined as preferring frequently co-occurred words over the correct answer.Consequently, LLMs struggle to recall facts whose subject and object rarely co-occur in the pre-training dataset although they are seen during finetuning.We show that co-occurrence bias remains despite scaling up model sizes or finetuning.Therefore, we suggest finetuning on a debiased dataset to mitigate the bias by filtering out biased samples whose subject-object co-occurrence count is high.Although debiased finetuning allows LLMs to memorize rare facts in the training set, it is not effective in recalling rare facts unseen during finetuning.Further research in mitigation will help build reliable language models by preventing potential errors.The code is available at https://github.com/CheongWoong/ impact_of_cooccurrence.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.017
metaresearch head score (Gemma)0.150
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.017
Threshold uncertainty score0.089

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0170.150
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0030.006
Open science0.0020.003
Research integrity0.0010.004
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.056
GPT teacher head0.366
Teacher spread0.309 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations10
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207