English
Related papers

Related papers: Verifiable Fine-Tuning for LLMs: Zero-Knowledge Tr…

200 papers

The fine-tuning technique in deep learning gives rise to an emerging lineage relationship among models. This lineage provides a promising perspective for addressing security concerns such as unauthorized model redistribution and false claim…

Cryptography and Security · Computer Science 2026-01-21 Zhuoyi Shang , Jiasen Li , Pengzhen Chen , Yanwei Liu , Xiaoyan Gu , Weiping Wang

Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training…

Computation and Language · Computer Science 2025-05-19 Xiaoying Zhang , Baolin Peng , Ye Tian , Jingyan Zhou , Yipeng Zhang , Haitao Mi , Helen Meng

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in…

Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…

Cryptography and Security · Computer Science 2026-04-09 Jeongho Yoon , Chanhee Park , Yongchan Chun , Hyeonseok Moon , Heuiseok Lim

Current methods for few-shot fine-tuning of pretrained masked language models (PLMs) require carefully engineered prompts and verbalizers for each new task to convert examples into a cloze-format that the PLM can score. In this work, we…

Computation and Language · Computer Science 2022-04-27 Rabeeh Karimi Mahabadi , Luke Zettlemoyer , James Henderson , Marzieh Saeidi , Lambert Mathias , Veselin Stoyanov , Majid Yazdani

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

Guaranteeing the correctness and factuality of language model (LM) outputs is a major open problem. In this work, we propose conformal factuality, a framework that can ensure high probability correctness guarantees for LMs by connecting…

Machine Learning · Computer Science 2024-02-20 Christopher Mohri , Tatsunori Hashimoto

Federated Learning has rapidly expanded from its original inception to now have a large body of research, several frameworks, and sold in a variety of commercial offerings. Thus, its security and robustness is of significant importance.…

Cryptography and Security · Computer Science 2025-10-02 Simone Bottoni , Giulio Zizzo , Stefano Braghin , Alberto Trombetta

We present a framework for verifying the deterministic structured computations surrounding a large language model rather than the model itself, extending a Lean 4 trust-boundary architecture to the generic interfaces of modern LLM…

Logic in Computer Science · Computer Science 2026-05-19 George Koomullil

Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs. Fine-tuning such models to downstream tasks is challenging because one can neither access the model's internal…

Machine Learning · Computer Science 2023-05-02 Maohao Shen , Soumya Ghosh , Prasanna Sattigeri , Subhro Das , Yuheng Bu , Gregory Wornell

Factual knowledge extraction aims to explicitly extract knowledge parameterized in pre-trained language models for application in downstream tasks. While prior work has been investigating the impact of supervised fine-tuning data on the…

Computation and Language · Computer Science 2025-05-30 Xuan Gong , Hanbo Huang , Shiyu Liang

In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which…

Computation and Language · Computer Science 2022-11-28 Yiqiao Jin , Xiting Wang , Yaru Hao , Yizhou Sun , Xing Xie

Document forgery poses a growing threat to legal, economic, and governmental processes, requiring increasingly sophisticated verification mechanisms. One approach involves the use of plausibility checks, rule-based procedures that assess…

Artificial Intelligence · Computer Science 2025-12-23 Valentin Schmidberger , Manuel Eberhardinger , Setareh Maghsudi , Johannes Maucher

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…

Systems and Control · Electrical Eng. & Systems 2025-04-24 Puja Chaudhury , Alexander Estornell , Michael Everett

We develop new conformal inference methods for obtaining validity guarantees on the output of large language models (LLMs). Prior work in conformal language modeling identifies a subset of the text that satisfies a high-probability…

Machine Learning · Statistics 2024-11-01 John J. Cherian , Isaac Gibbs , Emmanuel J. Candès

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Computation and Language · Computer Science 2024-10-16 Yihuai Hong , Yuelin Zou , Lijie Hu , Ziqian Zeng , Di Wang , Haiqin Yang

Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. We propose explanation-based…

Computation and Language · Computer Science 2023-06-07 Josh Magnus Ludan , Yixuan Meng , Tai Nguyen , Saurabh Shah , Qing Lyu , Marianna Apidianaki , Chris Callison-Burch

Low-Rank Adaptation (LoRA) is a widely adopted method for customizing large-scale language models. In distributed, untrusted training environments, an open source base model user may want to use LoRA weights created by an external…

Cryptography and Security · Computer Science 2025-01-27 Bidhan Roy , Peter Potash , Marcos Villagra

Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…

Computation and Language · Computer Science 2025-06-27 Xiaoshuang Ji , Zhendong Zhao , Xiaojun Chen , Xin Zhao , Zeyao Liu

Systematic reviews traditionally have taken considerable amounts of human time and energy to complete, in part due to the extensive number of titles and abstracts that must be reviewed for potential inclusion. Recently, researchers have…

Computation and Language · Computer Science 2026-03-27 Kweku Yamoah , Noah Schroeder , Emmanuel Dorley , Neha Rani , Caleb Schutz
‹ Prev 1 3 4 5 6 7 10 Next ›