Papers by Hayden Helm
Toward A Digital Twin of U.S. Congress (2026.findings-acl)
Copied to clipboard
| Challenge: | a virtual model of congresspersons based on a collection of language models meets the definition of a digital twin. |
| Approach: | They propose to use a daily-updated dataset to generate tweets from congresspersons . they show that a modern language model equipped with subsets of this dataset produces Tweets that are indistinguishable from actual Tweets posted by their physical counterparts. |
| Outcome: | The proposed model produces Tweets that are indistinguishable from actual tweets posted by congresspersons. |
A Model of the Language Process (2026.acl-long)
Copied to clipboard
| Challenge: | Language is a process that changes over time as new vocabulary emerges, word meanings shift, and narratives progress. |
| Approach: | They introduce a BERT style transformer encoder that models language by jointly learning to predict document contents and classify document publication dates. |
| Outcome: | The proposed model can predict document contents and classify document publication dates and accurately detects changes in word meanings. |
Statistical inference on black-box generative models in the data kernel perspective space (2025.findings-acl)
Copied to clipboard
| Challenge: | Generative models are capable of producing human-expert level content across a variety of topics and domains. |
| Approach: | They extend recent results on representations of black-box generative models to model-level statistical inference tasks. |
| Outcome: | The proposed models are effective for multiple inference tasks and meet or surpass human-level standards on benchmarks across a range of tasks. |
Tracking the perspectives of interacting language models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models produce high quality information at unprecedented rates . content produced by these models is propagated throughout forums that influence other models and human users . |
| Approach: | They propose a method for representing the perspective of individual models within a collection of LLMs. |
| Outcome: | The proposed method represents the perspective of individual models within a collection of LLMs in various simulated settings. |