activity
20182022
most citedExplaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions

19 citations · 34 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL202210 cited

ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data

Xiaochuang Han, Yulia Tsvetkov

Large pretrained language models have been performing increasingly well in a variety of downstream tasks via prompting. However, it remains unclear from where the model learns the…

cs.CL2021

Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates

Xiaochuang Han, Yulia Tsvetkov

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approac…

cs.CL2020

Fortifying Toxic Speech Detectors Against Veiled Toxicity

Xiaochuang Han, Yulia Tsvetkov

Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestatio…

cs.CL202019 cited

Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions

Xiaochuang Han, Byron C. Wallace, Yulia Tsvetkov

Modern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or th…

cs.CL20195 cited

No Permanent Friends or Enemies: Tracking Relationships between Nations from News

Xiaochuang Han, Eunsol Choi, Chenhao Tan

Understanding the dynamics of international politics is important yet challenging for civilians. In this work, we explore unsupervised neural models to infer relations between nati…

cs.CL2019

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Xiaochuang Han, Jacob Eisenstein

Contextualized word embeddings such as ELMo and BERT provide a foundation for strong performance across a wide range of natural language processing tasks by pretraining on large co…