17 citations · 27 across the 12 of their papers we have counts for
15 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…
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
Kia-Jüng Yang, Dominik Meier, Jiachen Zhao +2
Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms suc…
Approximate Diverse -nearest Neighbor Search in Vector Database
Jiachen Zhao, Xiao Yan, Eric Lo
Approximate -nearest neighbor search (A-NNS) is a core operation in vector databases, underpinning applications such as retrieval-augmented generation (RAG) and image retriev…
Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
Jiachen Zhao, Yiyou Sun, Weiyan Shi +1
Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the…
LatentFlow: Cross-Frequency Experimental Flow Reconstruction from Sparse Pressure via Latent Mapping
Junle Liu, Chang Liu, Yanyu Ke +5
Acquiring temporally high-frequency and spatially high-resolution turbulent wake flow fields in particle image velocimetry (PIV) experiments remains a significant challenge due to…
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…
QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge
Hongwei Bran Li, Fernando Navarro, Ivan Ezhov +77
Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a sign…
In-Context Exemplars as Clues to Retrieving from Large Associative Memory
Jiachen Zhao
Recently, large language models (LLMs) have made remarkable progress in natural language processing. The most representative ability of LLMs is in-context learning (ICL), which ena…
Student as an Inherent Denoiser of Noisy Teacher
Jiachen Zhao
Knowledge distillation (KD) has been widely employed to transfer knowledge from a large language model (LLM) to a specialized model in low-data regimes through pseudo label learnin…
Learning and Forgetting Unsafe Examples in Large Language Models
Jiachen Zhao, Zhun Deng, David Madras +2
As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning fro…
Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation
Jiachen Zhao, Wenlong Zhao, Andrew Drozdov +5
We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs)…
Large Language Models are In-context Teachers for Knowledge Reasoning
Jiachen Zhao, Zonghai Yao, Zhichao Yang +1
In this work, we study in-context teaching (ICT), where a teacher provides in-context example rationales to teach a student to reason over unseen cases. Human teachers are usually…
Biomedical image analysis competitions: The state of current participation practice
Matthias Eisenmann, Annika Reinke, Vivienn Weru +352
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known abou…
Trigger-free Event Detection via Derangement Reading Comprehension
Jiachen Zhao, Haiqin Yang
Event detection (ED), aiming to detect events from texts and categorize them, is vital to understanding actual happenings in real life. However, mainstream event detection models r…