AIConfPaper
← Search

Jiuding Sun

4 accepted papers

2025

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Jiuding Sun, Jing Huang, Sidharth Baskaran, Karel D'Oosterlinck, Christopher Potts, Michael Sklar +1
ICLR 2025poster

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 of a Nobel laureate*) and enable predictable manipulation. Distributed alignment search (DAS) leverages supervision fr…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

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

Jiuding Sun, Chantal Shaib, Byron C Wallace
ICLR 2024spotlight

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 particular strength in improving the performance of modestly sized LLMs, sometimes inducing performance competitive wit…

Cited by 49Source ↗PDF ↗code ↗Scholar ↗
2023

Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing

Lunyiu Nie, Jiuding Sun, Yanlin Wang, Lun Du, Shi Han, Dongmei Zhang +3
AAAI 2023technical

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task. Despite the promising performance, previous PLM-based approaches o…

Cited by 5Source ↗PDF ↗Scholar ↗
2022

GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation

Lunyiu Nie, Shulin Cao, Jiaxin Shi, Jiuding Sun, Qi Tian, Lei Hou +2
EMNLP 2022main

Subject to the huge semantic gap between natural and formal languages, neural semantic parsing is typically bottlenecked by its complexity of dealing with both input semantics and output syntax. Recent works have proposed several forms of supplementary supervision but none is generalized across mult…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗