Picture for Yangfeng Ji

Yangfeng Ji

Monte Carlo Sampling for Analyzing In-Context Examples

Add code
Mar 27, 2025
Viaarxiv icon

Sensing and Steering Stereotypes: Extracting and Applying Gender Representation Vectors in LLMs

Add code
Feb 27, 2025
Viaarxiv icon

In-Context Learning (and Unlearning) of Length Biases

Add code
Feb 10, 2025
Viaarxiv icon

RWKV-edge: Deeply Compressed RWKV for Resource-Constrained Devices

Add code
Dec 14, 2024
Viaarxiv icon

A Comparative Study of Learning Paradigms in Large Language Models via Intrinsic Dimension

Add code
Dec 09, 2024
Viaarxiv icon

TPIE: Topology-Preserved Image Editing With Text Instructions

Add code
Nov 22, 2024
Viaarxiv icon

Does Differential Privacy Impact Bias in Pretrained NLP Models?

Add code
Oct 24, 2024
Figure 1 for Does Differential Privacy Impact Bias in Pretrained NLP Models?
Figure 2 for Does Differential Privacy Impact Bias in Pretrained NLP Models?
Figure 3 for Does Differential Privacy Impact Bias in Pretrained NLP Models?
Figure 4 for Does Differential Privacy Impact Bias in Pretrained NLP Models?
Viaarxiv icon

The Mismeasure of Man and Models: Evaluating Allocational Harms in Large Language Models

Add code
Aug 02, 2024
Viaarxiv icon

Improve Temporal Awareness of LLMs for Sequential Recommendation

Add code
May 05, 2024
Figure 1 for Improve Temporal Awareness of LLMs for Sequential Recommendation
Figure 2 for Improve Temporal Awareness of LLMs for Sequential Recommendation
Figure 3 for Improve Temporal Awareness of LLMs for Sequential Recommendation
Figure 4 for Improve Temporal Awareness of LLMs for Sequential Recommendation
Viaarxiv icon

Addressing Both Statistical and Causal Gender Fairness in NLP Models

Add code
Mar 30, 2024
Viaarxiv icon