Search Results for author:
Found 8 papers, 4 papers with code
Optimizing Language Models for Human Preferences is a Causal Inference Problem
In this paper, we present an initial exploration of language model optimization for human preferences from direct outcome datasets, where each sample consists of a text and an associated numerical outcome measuring the reader's response.
Text-Transport: Toward Learning Causal Effects of Natural Language
To address this issue, we leverage the notion of distribution shift to describe an estimator that transports causal effects between domains, bypassing the need for strong assumptions in the target domain.
SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations
Moreover, we find that SenteCon outperforms existing interpretable language representations with respect to both its downstream performance and its agreement with human characterizations of the text.
Counterfactual Augmentation for Multimodal Learning Under Presentation Bias
In real-world machine learning systems, labels are often derived from user behaviors that the system wishes to encourage.
SeedBERT: Recovering Annotator Rating Distributions from an Aggregated Label
However, machine learning datasets commonly have just one "ground truth" label for each sample, so models trained on these labels may not perform well on tasks that are subjective in nature.
Stage-wise Fine-tuning for Graph-to-Text Generation
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders.
Ranked #3 on
Data-to-Text Generation
on WebNLG
(using extra training data)
Context-Dependent Models for Predicting and Characterizing Facial Expressiveness
In recent years, extensive research has emerged in affective computing on topics like automatic emotion recognition and determining the signals that characterize individual emotions.
