Papers by David Evans
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Traditional adversarial examples involve finding a small perturbation that does not change an input’s true label but confuses the classifier into outputting a different prediction. |
| Approach: | They propose to use contrastive learning to increase model robustness against fickle adversarial examples by reducing the vulnerability of adversarials to fickle ones. |
| Outcome: | The proposed method improves model robustness against fickle and obstinate adversarial examples. |
Grounding Characters and Places in Narrative Text (2023.acl-long)
Copied to clipboard
| Challenge: | Prior work has analyzed characters and locations from text independently without grounding characters to their locations in narrative time. |
| Approach: | They propose a task to assign a spatial relationship category for every character and location co-mention within a window of text, taking into account linguistic context, narrative tense, and temporal scope. |
| Outcome: | The proposed model allows to test hypotheses on mobility and domestic space . women as characters tend to occupy more interior space than men, the model shows . |
Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Having high quality annotated data is crucial for training supervised machine learning models. |
| Approach: | They propose automated methods to improve NLP datasets by viewing them as graphs with expected semantic properties. |
| Outcome: | The proposed methods improve paraphrase models on pre-trained datasets. |
Unsupervised Concept Vector Extraction for Bias Control in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. |
| Approach: | They propose a method that extracts concept representations via probability weighting without labeled data and efficiently selects a steering vector for measuring and manipulating the model’s representation. |
| Outcome: | The proposed method can be used to predict gender bias and generalizes to racial bias. |
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Large language models are shown to present privacy risks through memorization of training data, but little attention has been given to the fine-tuning phase. |
| Approach: | They empirically study memorization of fine-tuning methods using membership inference and extraction attacks and show that fine-timing the head of the model has the highest susceptibility to attacks. |
| Outcome: | The proposed methods have the highest memorization risk, whereas the smaller adapters are less vulnerable to known extraction attacks. |
Inferring Events from Time Series using Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work on reasoning about time series in conjunction with natural language has largely overlooked event descriptions and focused on tasks involving just numeric data like trend analysis or anomaly detection. |
| Approach: | They propose a method for generating tasks that test a model’s ability to reason about events associated with time series data based on sports data and develop a benchmarking method. |
| Outcome: | The proposed method can infer unobserved events from time series data, even when providing minimal context. |
Addressing Both Statistical and Causal Gender Fairness in NLP Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Statistical fairness stipulates equivalent outcomes for all protected groups, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. |
| Approach: | They propose to use statistical and causal debiasing methods to reduce gender bias in NLP models. |
| Outcome: | The proposed methods reduce gender bias measured by the targeted metric, but not on other bias metrics. |
Pointwise Paraphrase Appraisal is Potentially Problematic (2020.acl-srw)
Copied to clipboard
| Challenge: | prevailing methods for paraphrase identification models are binary classification problems . current methods do not provide consistent and robust performance on unseen samples and real world problems. |
| Approach: | They propose to use binary classification to evaluate paraphrase identification models . they propose to improve methods for fine-tuning BERT models by pairing two sentences as one sequence . |
| Outcome: | The proposed methods may fail on simple tasks like identifying pairs with two identical sentences. |