MétaCan
Menu
Back to cohort

Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs

2025· article· en· W4412889746 on OpenAlexfundno aff
Ziling Cheng, Meng Cao, Marc-Antoine Rondeau

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAnomaly Detection Techniques and Applications
Canadian institutionsnot available
FundersCanadian Institute for Advanced ResearchNvidia
KeywordsGeneralizationContext (archaeology)Class (philosophy)Computer scienceCognitive psychologyArtificial intelligencePsychologySocial psychologyEconometricsMathematicsGeography

Abstract

fetched live from OpenAlex

The widespread success of large language models (LLMs) on NLP benchmarks has been accompanied by concerns that LLMs function primarily as stochastic parrots that reproduce texts similar to what they saw during pre-training, often erroneously.But what is the nature of their errors, and do these errors exhibit any regularities?In this work, we examine irrelevant context hallucinations, in which models integrate misleading contextual cues into their predictions.Through behavioral analysis, we show that these errors result from a structured yet flawed mechanism that we term class-based (mis)generalization, in which models combine abstract class cues with features extracted from the query or context to derive answers.Furthermore, mechanistic interpretability experiments on Llama-3, Mistral, and Pythia across 39 factual recall relation types reveal that this behavior is reflected in the model's internal computations: (i) abstract class representations are constructed in lower layers before being refined into specific answers in higher layers, (ii) feature selection is governed by two competing circuits -one prioritizing direct query-based reasoning, the other incorporating contextual cues -whose relative influences determine the final output.Our findings provide a more nuanced perspective on the stochastic parrot argument: through form-based training, LLMs can exhibit generalization leveraging abstractions, albeit in unreliable ways based on contextual cues -what we term stochastic chameleons. 1 * Equal contribution.

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)0.003
metaresearch head score (Gemma)0.027
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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.003
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.027
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.002
Scholarly communication0.0020.005
Open science0.0010.003
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.000

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 head0.010
GPT teacher head0.268
Teacher spread0.258 · 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

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAnomaly Detection Techniques and ApplicationsFrench-language works237,207