Papers by Kellin Pelrine
Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Named-Entity Recognition (NER) on escort ads are not sufficient to extract person names from the text of the ad. |
| Approach: | They propose to use a model to extract person names from escort ads to capture ambiguous names and adapt to adversarial changes in the text. |
| Outcome: | The proposed model shows 19% improvement on average in the F1 classification score compared to previous state-of-the-art in two domain-specific datasets. |
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility (2025.emnlp-main)
Copied to clipboard
Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh, Tom Tseng, Julius Broomfield, Adam Gleave, Kellin Pelrine
| Challenge: | a recent study shows that fine-tuning can produce helpful-only models with safeguards destroyed. |
| Approach: | They propose a method for fine-tuning models to generate detailed, high-quality responses to harmful requests. |
| Outcome: | The proposed method produces helpful-only models with safeguards destroyed . OpenAI, Google, and Anthropic models will fully comply with requests for CBRN assistance . |
SWEET - Weakly Supervised Person Name Extraction for Fighting Human Trafficking (2023.findings-emnlp)
Copied to clipboard
| Challenge: | SWEET is a weak supervision pipeline for extracting person names from noisy escort ads . it does not require any human annotators and labeling, which is incredibly important . |
| Approach: | They propose a weak supervision pipeline SWEET: Supervise Weakly for Entity Extraction to fight Trafficking for extracting person names from noisy escort ads. |
| Outcome: | The proposed weak supervision pipeline outperforms the previous method by 9% on domain data and generalizes to common benchmark datasets. |
Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4 (2023.emnlp-main)
Copied to clipboard
Kellin Pelrine, Anne Imouza, Camille Thibault, Meilina Reksoprodjo, Caleb Gupta, Joel Christoph, Jean-François Godbout, Reihaneh Rabbany
| Challenge: | Misinformation is a critical societal challenge, and current approaches have yet to produce an effective solution. |
| Approach: | They propose to focus on generalization, uncertainty and how to leverage large language models . they propose techniques to handle uncertainty that can detect impossible examples and strongly improve outcomes . |
| Outcome: | The proposed tools outperform previous methods in multiple settings and languages. |
The Structural Safety Generalization Problem (2025.findings-acl)
Copied to clipboard
Julius Broomfield, Tom Gibbs, George Ingebretsen, Ethan Kosak-Hine, Tia Nasir, Jason Zhang, Reihaneh Iranmanesh, Sara Pieri, Reihaneh Rabbany, Kellin Pelrine
| Challenge: | LLM jailbreaks are a widespread safety challenge. |
| Approach: | They propose a structure-rewriting guardrail that allows for more efficient safety assessment . single-turn attacks are the most extensively explored in the literature . |
| Outcome: | The proposed framework can be used to enable new defenses, the authors show . they show that the proposed framework reduces the risk of harmful inputs . |