8 papers
Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning
Xinrui Chen, Jianhao Zhang, Ou Wu +1
Fine-tuning safety aligned large language models (LLMs) on downstream data improves adaptation but may erode learned safety behavior. Existing methods use fixed safety examples, gl…
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
Liu Qing, Ou Wu, Yi Du
Token selection is pivotal for effective LLM post-training. However, existing methods mostly rely on local heuristics and rarely formulate token selection as a principled valuation…
Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
Haoben Huang, Shuxin Liu, Ou Wu +1
Single-edit updates in large language models can trigger ripple effects across local knowledge neighborhoods: desirable propagation to related facts and unintended perturbation of…
Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design
Ou Wu, Yingjun Deng
Token economics has emerged as a useful lens for understanding resource allocation, value creation, and pricing in large language model systems. While recent work has increasingly…
One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
Xinrui Chen, Liu Yang, Ou Wu
In Large Language Model (LLM) fine-tuning, parameter and data selection are common strategies for reducing fine-tuning cost, yet they are typically driven by separate scoring mecha…
Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion
Ou Wu
Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved samples through selection, aug…