Papers by Pegah Jandaghi
Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality (2022.emnlp-main)
Copied to clipboard
| Challenge: | Currently, human communication models fail to explicitly model common ground (CG) . less than half of the responses in current data is rated as high quality . |
| Approach: | They propose a dataset that annotates dialogues with explicit CG and solicits 9k diverse responses each following one common ground. |
| Outcome: | The proposed dataset annotates dialogues with explicit CG and solicits 9k diverse responses each following one common ground. |
Probing Commonsense Explanation in Dialogue Response Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, response generation (RG) models do not understand human communication intents. |
| Approach: | They propose to examine commonsense reasoning implicitly to determine whether RG models produce coherent responses in conversations. |
| Outcome: | The proposed probing settings show that RG models fail to capture the logical relations between commonsense explanations and responses and fine-tuning on in-domain data do not lead to understanding of CSR for RG. |
FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue (2022.emnlp-main)
Copied to clipboard
Alon Albalak, Yi-Lin Tuan, Pegah Jandaghi, Connor Pryor, Luke Yoffe, Deepak Ramachandran, Lise Getoor, Jay Pujara, William Yang Wang
| Challenge: | Prior studies of task transfer in dialogue consider only 2-4 tasks, focus on multitasks. |
| Approach: | They propose a benchmark for FEw-sample TAsk transfer in open-domain dialogue. |
| Outcome: | The proposed benchmark analyzes the transferability between 132 source-target task pairs and provides a baseline for future work. |
Faithful Persona-based Conversational Dataset Generation with Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for training conversational AI models do not sufficiently model their users. |
| Approach: | They propose a generator-critic architecture framework to expand the initial dataset while improving the quality of its conversations. |
| Outcome: | The proposed framework expands the initial dataset while improving the quality of its conversations. |
A Systematic Analysis of Base Model Choice for Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) and reward modeling are key to training powerful large language models (LLMs). |
| Approach: | They propose to combine RLHF and reward modeling to boost model selection . they also demonstrate that a small set of benchmarks could be combined to boost the model selection. |
| Outcome: | The results show that the model selection can be improved by up to 14% compared to the most common (default) choice. |