research
∙
08/08/2023
In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning
In this note, we explore inference-time alignment through in-context lea...
share
research
∙
06/26/2023
Understanding In-Context Learning via Supportive Pretraining Data
In-context learning (ICL) improves language models' performance on a var...
research
∙
05/24/2023
Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
Language models (LMs) often struggle to pay enough attention to the inpu...
research
∙
05/17/2023
Can Language Models Solve Graph Problems in Natural Language?
Large language models (LLMs) are increasingly adopted for a variety of t...
research
∙
12/20/2022
Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
Large language models can perform new tasks in a zero-shot fashion, give...
research
∙
05/25/2022
ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data
Large pretrained language models have been performing increasingly well ...
research
∙
10/07/2021
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates
Among the most critical limitations of deep learning NLP models are thei...
research
∙
10/07/2020
Fortifying Toxic Speech Detectors Against Veiled Toxicity
Modern toxic speech detectors are incompetent in recognizing disguised o...
research
∙
05/14/2020
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions
Modern deep learning models for NLP are notoriously opaque. This has mot...
research
∙
04/18/2019
No Permanent Friends or Enemies: Tracking Relationships between Nations from News
Understanding the dynamics of international politics is important yet ch...
research
∙
04/04/2019
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling
Contextualized word embeddings such as ELMo and BERT provide a foundatio...
research
∙
04/04/2019
Unsupervised Domain Adaptation of Contextualized Embeddings: A Case Study in Early Modern English
Contextualized word embeddings such as ELMo and BERT provide a foundatio...
research
∙
09/18/2018