SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.08765 · 2026

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning

Sijia Liu, Yihua Zhang, Renjie Gu, Jiazhen Du, Method B:, A Sarin

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2605.08765.json · badge: /api/ran/2605.08765.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
OPTML-Group/ReVa canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
forward_with_cache Ran
ran, honoured the contract we drafted
OPTML-Group/ReVa/src/train/reva/utils.py
pointer only (licence: NONE) · get_code("17f8adc99ab2c7a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OPTML-Group/ReVa when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_params Ran
ran; our contract draft was wrong, not the code
OPTML-Group/ReVa/src/train/reva/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from optml-group/mu-coreset, is pointer only (licence: NONE) · get_code("db42ee03f6308ed9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OPTML-Group/ReVa when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_model Ran
ran; our contract draft was wrong, not the code
OPTML-Group/ReVa/src/train/reva/utils.py
pointer only (licence: NONE) · get_code("7bdf184a0ba57b39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OPTML-Group/ReVa when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unlearncollector Ran
ran; our contract draft was wrong, not the code
OPTML-Group/ReVa/src/eval/dataset/Base.py
pointer only (licence: NONE) · get_code("a378b7ead7ef288e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OPTML-Group/ReVa when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_params 4 other papers
4 dated earlier
2403.03218 (2024-03)
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
2406.13356 (2024-06)
UNLEARNING OR OBFUSCATING? JOGGING THE MEM-ORY OF UNLEARNED LLMS VIA BENIGN RELEARNING CONTENT WARNING: THIS MANUSCRIPT CONTAINS EXAMPLES OF HARMFUL/HAZARDOUS TEXT
2408.06223 (2024-08)
On Effects of Steering Latent Representation for Large Language Model Unlearning
and 1 more not named here
load_model 2 other papers
2 dated earlier
2403.03218 (2024-03)
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
2408.06223 (2024-08)
On Effects of Steering Latent Representation for Large Language Model Unlearning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising safety and trust concerns. According to prior literature on LLM honesty, such behaviors are often associated with dishonesty. This motivates us to investigate the notion of honesty in the context of model unlearning. We propose a formal definition of unlearning honesty, which includes: (1) preserving both utility and honesty on retained knowledge, and (2) ensuring effective forgetting while encouraging the model to acknowledge its limitations and respond consistently to questions related to forgotten knowledge. To systematically evaluate the honesty of unlearning, we introduce a suite of metrics that cover utility, honesty on the retained set, effectiveness of forgetting, rejection rate and refusal stability in Q&A and MCQ settings. Evaluating 9 methods across 3 mainstream families shows that all current methods fail to meet these standards. After experimental and theoretical analyses, we present ReVa, a representation-alignment procedure that fine-tunes feature-randomized unlearned models to better acknowledge forgotten knowledge. On Q&A tasks from the forget set, ReVa achieves the highest rejection rate after two rounds of interaction, nearly doubling the performance of the second-best method. Remarkably, It also improves honesty on the retained set. We release our data and code at https://github.com/OPTML-Group/ReVa.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.08765")
get_code_for_paper("2605.08765")
have("2605.08765")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2605.08765.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2605.08765.svg)](https://syntology.ai/paper/2605.08765)

Connect an agent — have() is free.