activity
20222026
most citedEDUKG: a Heterogeneous Sustainable K-12 Educational Knowledge Graph

4 citations · 6 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2025

HyperSteer: Activation Steering at Scale with Hypernetworks

Jiuding Sun, Sidharth Baskaran, Zhengxuan Wu +3

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoe…

cs.CL2025

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Jiuding Sun, Jing Huang, Sidharth Baskaran +4

Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts(e.g., the birth year…

cs.CL2024

Open (Clinical) LLMs are Sensitive to Instruction Phrasings

Alberto Mario Ceballos Arroyo, Monica Munnangi, Jiuding Sun +4

Instruction-tuned Large Language Models (LLMs) can perform a wide range of tasks given natural language instructions to do so, but they are sensitive to how such instructions are p…

cs.CL2024

Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores

Chantal Shaib, Venkata S. Govindarajan, Joe Barrow +4

The diversity across outputs generated by LLMs shapes perception of their quality and utility. High lexical diversity is often desirable, but there is no standard method to measure…

cs.CL2023

Future Lens: Anticipating Subsequent Tokens from a Single Hidden State

Koyena Pal, Jiuding Sun, Andrew Yuan +2

We conjecture that hidden state vectors corresponding to individual input tokens encode information sufficient to accurately predict several tokens ahead. More concretely, in this…

cs.CL2023

Evaluating the Zero-shot Robustness of Instruction-tuned Language Models

Jiuding Sun, Chantal Shaib, Byron C. Wallace

Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown…