activity
20242026
collaborators

9 papers

cs.CL2026

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

Jiachen Zhao, Zhengxuan Wu, Aryaman Arora +3

The mechanisms behind LLMs' broad over-generalization beyond training examples remain unclear. Emergent misalignment (EM) offers a striking case study: finetuning on narrow tasks i…

cs.LG2026

PreFT: Prefill-only finetuning for efficient inference

Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu +4

Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with…

cs.IR2026

A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems

Yiming Zhu, Xu Liu, Ziyun Xu +9

Conventional recommendation systems frequently fail to fully exploit the high-dimensional semantic signals inherent in multimedia content, thereby limiting the fidelity of user pre…

cs.CL2026

ADAG: Automatically Describing Attribution Graphs

Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt +1

In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular output and how they affected eac…

cs.CL2026

Language Model Circuits Are Sparse in the Neuron Basis

Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt +1

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has…

cs.CL2025

LLMs Encode Harmfulness and Refusal Separately

Jiachen Zhao, Jing Huang, Zhengxuan Wu +2

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by…