Search Results for author:
Found 13 papers, 7 papers with code
ComplexDataLab at W-NUT 2020 Task 2: Detecting Informative COVID-19 Tweets by Attending over Linked Documents
Given the global scale of COVID-19 and the flood of social media content related to it, how can we find informative discussions?
Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking
In this paper, we propose NEAT (Name Extraction Against Trafficking) for extracting person names.
Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
We propose an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions.
Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation
Recent large language models (LLMs) have been shown to be effective for misinformation detection.
Uncertainty Resolution in Misinformation Detection
Misinformation poses a variety of risks, such as undermining public trust and distorting factual discourse.
Exploiting Novel GPT-4 APIs
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API.
Party Prediction for Twitter
A large number of studies on social media compare the behaviour of users from different political parties.
Open, Closed, or Small Language Models for Text Classification?
Recent advancements in large language models have demonstrated remarkable capabilities across various NLP tasks.
Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4
We propose focusing on generalization, uncertainty, and how to leverage recent large language models, in order to create more practical tools to evaluate information veracity in contexts where perfect classification is impossible.
Adversarial Policies Beat Superhuman Go AIs
The core vulnerability uncovered by our attack persists even in KataGo agents adversarially trained to defend against our attack.
Active Keyword Selection to Track Evolving Topics on Twitter
How can we study social interactions on evolving topics at a mass scale?
Towards Better Evaluation for Dynamic Link Prediction
To evaluate against more difficult negative edges, we introduce two more challenging negative sampling strategies that improve robustness and better match real-world applications.
The Surprising Performance of Simple Baselines for Misinformation Detection
As social media becomes increasingly prominent in our day to day lives, it is increasingly important to detect informative content and prevent the spread of disinformation and unverified rumours.
