Papers by Suhong Moon
Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions (2025.acl-long)
Copied to clipboard
| Challenge: | Prior studies have failed to accurately predict distribution of survey responses from human subjects. |
| Approach: | They propose to fine-tune large language models to predict human response distributions by leveraging unique structural characteristics of survey data. |
| Outcome: | The proposed model can capture group-specific variability in public opinions, generalizing to unseen subpopulations, survey waves and question topics, and different survey families. |
Graph-Based Alternatives to LLMs for Human Simulation (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are a popular approach for simulating human behaviors, yet it remains unclear if they are necessary for all simulation tasks. |
| Approach: | They propose a graph neural network that can match or surpass strong LLMs for close-ended simulations. |
| Outcome: | The proposed model outperforms strongest LLM-based methods across three datasets and three evaluation settings. |
TinyAgent: Function Calling at the Edge (2024.emnlp-demo)
Copied to clipboard
Lutfi Erdogan, Nicholas Lee, Siddharth Jha, Sehoon Kim, Ryan Tabrizi, Suhong Moon, Coleman Hooper, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami
| Challenge: | Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries. |
| Approach: | They propose an end-to-end framework for training and deploying task-specific small language model agents capable of function calling for driving agentic systems at the edge. |
| Outcome: | The proposed model outperforms existing models by reducing the input prompt length and quantizing the inference speed. |
Virtual Personas for Language Models via an Anthology of Backstories (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are trained from vast repositories of text authored by millions of distinct authors, reflecting an enormous diversity of human traits. |
| Approach: | They propose a method for conditioning LLMs to particular virtual personas by harnessing open-ended life narratives, which they refer to as backstories, and demonstrate that it improves consistency and reliability of experimental outcomes. |
| Outcome: | The proposed method improves consistency and reliability of experimental outcomes while ensuring better representation of diverse sub-populations. |