MétaCan
Menu
Back to cohort

REVIVING YOUR MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing

2025· article· W4416035385 on OpenAlexfundno aff
Aly M. Kassem, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsnot available
FundersAlliance de recherche numérique du CanadaCanadian Institute for Advanced Research
KeywordsAction (physics)Feature (linguistics)Identification (biology)Perspective (graphical)Key (lock)

Abstract

fetched live from OpenAlex

LLMs are frequently fine-tuned or unlearned to adapt to new tasks or eliminate undesirable behaviors.While existing evaluation methods assess performance after such interventions, there remains no general approach for detecting unintended side effects-such as unlearning biology content degrading performance on chemistry tasks, particularly when these effects are unpredictable or emergent.To address this issue, we introduce MNEME, Model diffiNg for Evaluating Mechanistic Effects, a framework for identifying these side effects using sparse model diffing.MNEME compares base and fine-tuned models on out-of-distribution (OOD) data (e.g., The Pile, LMSYS-Chat-1M), without access to fine-tuning data, to isolate behavioral shifts.Applied to five LLMs across three scenarios, WMDP knowledge unlearning, emergent misalignment, and benign finetuning, MNEME achieves up to 95% accuracy in predicting side effects, aligning with known benchmarks and requiring no custom heuristics.Our results demonstrate that sparse probing and diffing offer a scalable and automated lens into fine-tuning-induced model changes, providing practical tools for understanding and managing LLM behavior. 1* MNEME refers to Mnmosyn, the Greek Titan goddess of memory, whose name derives from the Greek word mnm ("memory").

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.004
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.769
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.004
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.002
Science and technology studies0.0020.000
Scholarly communication0.0010.001
Open science0.0020.003
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.024
GPT teacher head0.275
Teacher spread0.251 · 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 teacher head, not a consensus.

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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicExplainable Artificial Intelligence (XAI)French-language works237,207