Toward conversational interpretations of neural networks: data collection
Neural networks are powerful techniques for automated decision making. However, they are also blackboxes, which human experts find difficult to understand. Recent work performed at NTU and internationally suggests that conversation is an effective form of interpreting neural networks to layperson us...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/181279 |
| _version_ | 1824453403399421952 |
|---|---|
| author | Yeow, Ming Xuan |
| author2 | Li Boyang |
| author_facet | Li Boyang Yeow, Ming Xuan |
| author_sort | Yeow, Ming Xuan |
| collection | NTU |
| description | Neural networks are powerful techniques for automated decision making. However, they are also blackboxes, which human experts find difficult to understand. Recent work performed at NTU and internationally suggests that conversation is an effective form of interpreting neural networks to layperson users. In this project, we aim to collected conversation data where layperson users interact with human experts, who explain the neural networks to them. We then finetune an LLM, in an attempt to combine conversational AI with XAI. |
| first_indexed | 2025-02-19T03:05:52Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/181279 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:05:52Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1812792024-11-21T08:37:58Z Toward conversational interpretations of neural networks: data collection Yeow, Ming Xuan Li Boyang College of Computing and Data Science boyang.li@ntu.edu.sg Computer and Information Science Computer science Machine learning Explainable AI LLM Neural networks are powerful techniques for automated decision making. However, they are also blackboxes, which human experts find difficult to understand. Recent work performed at NTU and internationally suggests that conversation is an effective form of interpreting neural networks to layperson users. In this project, we aim to collected conversation data where layperson users interact with human experts, who explain the neural networks to them. We then finetune an LLM, in an attempt to combine conversational AI with XAI. Bachelor's degree 2024-11-21T08:37:57Z 2024-11-21T08:37:57Z 2024 Final Year Project (FYP) Yeow, M. X. (2024). Toward conversational interpretations of neural networks: data collection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181279 https://hdl.handle.net/10356/181279 en image/png image/png image/png image/png application/pdf text/plain text/plain Nanyang Technological University |
| spellingShingle | Computer and Information Science Computer science Machine learning Explainable AI LLM Yeow, Ming Xuan Toward conversational interpretations of neural networks: data collection |
| title | Toward conversational interpretations of neural networks: data collection |
| title_full | Toward conversational interpretations of neural networks: data collection |
| title_fullStr | Toward conversational interpretations of neural networks: data collection |
| title_full_unstemmed | Toward conversational interpretations of neural networks: data collection |
| title_short | Toward conversational interpretations of neural networks: data collection |
| title_sort | toward conversational interpretations of neural networks data collection |
| topic | Computer and Information Science Computer science Machine learning Explainable AI LLM |
| url | https://hdl.handle.net/10356/181279 |
| work_keys_str_mv | AT yeowmingxuan towardconversationalinterpretationsofneuralnetworksdatacollection |