arXiv AI August 24, 2026 By Snigdha Paul, Manasi Patwardhan, Arman Cohan

Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning

The paper introduces the task of Scientific Claim Unlearning and presents a new benchmark, SciUnlearn, to evaluate it. It highlights that language models trained on static scientific corpora risk disseminating outdated or retracted claims as scientific knowledge evolves. Current machine unlearning methods fail to effectively remove claim-level knowledge, often only suppressing it superficially, underscoring the need for specialized techniques for structured knowledge removal.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 16

OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets

arXiv:2607. 13037v1 Announce Type: new Abstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author.

By Haolin Xue

efficiency

arXiv AI

5d ago

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

The paper introduces GRAPHSU, a graph‑guided selective unlearning method for language models that expands deletion beyond explicitly identified forget seeds. By constructing a weighted support‑route graph and propagating deletion pressure, GRAPHSU applies graded forgetting to high‑risk neighboring examples. Experiments on the TOFU and PISTOL benchmarks with GPT‑2 Medium and Llama‑3.2‑3B‑Instruct show that GRAPHSU achieves the lowest utility‑feasible soft leakage, reducing leakage by up to 49.5 percentage points compared to a seed‑only baseline.

By Waqas Khan, Tabinda Sarwar, Jingyue Cong, Xun Yi, Estrid He

llms fine-tuning benchmarks safety

arXiv Computation and Language

Aug 25

CALIBURN: Self-Calibrated LLM Unlearning Alignment

CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.

By Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu

llms benchmarks safety

arXiv Machine Learning

Jul 13

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

arXiv:2607. 09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety.

By Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein

llms benchmarks safety

arXiv Machine Learning

1d ago

On the Recoverability of Private Information Unlearning in Large Language Models

arXiv:2608.29943v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...

By Shicheng Hu, Runzhi Tian, Ziqiao Wang, Yongyi Mao

llms safety

arXiv AI

Aug 10

In-Context Examples Suppress Scientific Knowledge Recall in LLMs

arXiv:2604. 27540v2 Announce Type: replace Abstract: Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data.

By Chaemin Jang, Woojin Park, Hyeok Yun, Dongman Lee, Jihee Kim

llms

One email a morning, machine-written

Related stories

OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

CALIBURN: Self-Calibrated LLM Unlearning Alignment

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

On the Recoverability of Private Information Unlearning in Large Language Models

In-Context Examples Suppress Scientific Knowledge Recall in LLMs