Papers by Siyi Guo
Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communities (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies treat ideology as a liberal/conservative binary and fail to capture the spectrum of ideologies that may organically emerge in interconnected online communities. |
| Approach: | They propose a method that uses finetuning language models to probe nuanced ideologies of online communities by analyzing discussions of the 2020 election on Twitter. |
| Outcome: | The proposed approach shows higher alignment than baselines for the proposed approach. |
Community-Cross-Instruct: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities (2024.emnlp-main)
Copied to clipboard
| Challenge: | Social scientists use surveys to learn opinions and beliefs of populations, but these methods are slow, costly, and prone to biases. |
| Approach: | They propose a framework for aligning large language models to online communities by finetuning instruction-output pairs by an advanced LLM to elicit their beliefs. |
| Outcome: | The proposed framework enables cost-effective and automated surveying of diverse online communities. |
Whose Emotions and Moral Sentiments do Language Models Reflect? (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing research has focused on positional alignment, which measures how closely the models mimic the opinions and stances of different social groups. |
| Approach: | They define the problem of affective alignment, which measures how LMs’ emotional and moral tone represents those of different groups. |
| Outcome: | The results show that the models represent the perspectives of some social groups better than others, suggesting a systemic bias within LMs. |