Language Model Robustness

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 46% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 338

All topics

RAFP: Identifying LLM Lineages via Rare-Region Fingerprints
May 19, 2025Yun-Yun Tsai, Jia Hao Liang, Chuan Guo +2Language Model Fingerprinting Language Model Robustness
Columbia University / Meta · New York / Menlo Park, USA · MIT +5
Unified Enhancement of the Generalization and Robustness of Language Models via Bi-Stage Optimization
Mar 19, 2025Yudao Sun, Juan Yin, Juan Zhao +3Adversarial Training Neural Network Generalization
Department of New Networks, Peng Cheng Laboratory, Shenzhen 518055, China · Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore 117576 · School of Data Science and Artificial Intelligence, Chang’an University, Shaanxi, 710064, China
Homogeneity Bias in Open-Weight LLMs Is Robust to Decoding Hyperparameters
Jan 4, 2025Messi H. J. LeeSocial Bias in Language Models Open-Weight Language Models
Independent Researcher · Seoul, Republic of Korea
BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
Aug 8, 2024Yupeng Chang, Yi Chang, Yuan WuSocial Bias in Language Models Low-Rank Adaptation
School of Artificial Intelligence, Jilin University · Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University · International Center of Future Science, Jilin University
VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise
Date pendingSina Mansouri, Mohit Marvania, Vibhavari Ashok Shihorkar +5Healthcare LLM Reliability
Department of Computer Science, George Mason University · Department of Health Administration and Policy, College of Public Health, George Mason University · Department of Science, George Mason University
TREAT: Evaluating Access to Formal Knowledge across Equivalent Mathematical Representations
Date pendingFateme Mazdarani, Carlos ToxtliMathematical Reasoning Benchmarks Language Model Robustness
School of Computing Clemson University Clemson, SC, USA
'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
Date pendingFawzia Zehra (Fuzzy), Kara-Isitt, Sonal Khosla +1Multilingual Language Model Evaluation Language Model Safety Evaluation
Brunel University of London, UK · Hasso Plattner Institute Potsdam, Germany
LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text
Date pendingSungjune Lee, Myungjoo KangLLM Evaluation Structured Output Generation
Seoul National University

May 19, 2025, cs.LGJ/K move · Enter open · S save

RAFP: Identifying LLM Lineages via Rare-Region Fingerprints

Yun-Yun Tsai, Jia Hao Liang, Chuan Guo, Junfeng Yang+1

Columbia University / Meta · New York / Menlo Park, USA · MIT+5

Language Model Fingerprinting Language Model Robustness

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly released under restricted licenses, creating a growing need for robust model ownership verification. Existing fingerprinting methods are often fragile under downstream finetuning, require invasive training modifications, or fail in black-box settings. We introduce RAFP, a robust framework for identifying LLM lineages via rare-region fingerprints. Our key insight is that downstream finetuning primarily updates common high-density language behaviors, while low-probability prompt regions receive weak optimization signal and limited gradient alignment under finetuned distribution. As a result, rare prompt-response behaviors remain stable across common model adaptations. RAFP is non-invasive, constructing fingerprints via discrete gradient-based optimization over rare prompts without modifying model weights. We provide a theoretical analysis showing that the likelihood change of rare-region fingerprints under finetuning remains bounded. Experiments across four LLM families and multiple downstream adaptations, including supervised finetuning, LoRA, quantization, prompt-template variation, and decoding changes, show that RAFP achieves strong fingerprint persistence and substantially outperforms prior fingerprinting baselines in black-box settings.

Momentum

Related topics

Latest papers 338