10 papers
The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs
Jiachen Zhao, Zhengxuan Wu, David Bau +1
Language models are routinely fine-tuned under a fixed context, such as a generic system prompt, persona or domain-specific instruction, yet the learned behavior sometimes stays co…
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…
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…
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…
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…
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…
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…
Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
Joakim Edin, Casper L. Christensen, Róbert Csordás +5
Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis. Mos…
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
Zhengxuan Wu, Yuhao Zhang, Peng Qi +6
Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between…
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
Shiqi Chen, Miao Xiong, Junteng Liu +4
Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into th…