Picture for Saab Mansour

Saab Mansour

DFlow: Diverse Dialogue Flow Simulation with Large Language Models

Add code
Oct 18, 2024
Viaarxiv icon

Structured List-Grounded Question Answering

Add code
Oct 04, 2024
Viaarxiv icon

Fine-grained, Multi-dimensional Summarization Evaluation with LLMs

Add code
Jul 09, 2024
Viaarxiv icon

FineSurE: Fine-grained Summarization Evaluation using LLMs

Add code
Jul 01, 2024
Viaarxiv icon

CERET: Cost-Effective Extrinsic Refinement for Text Generation

Add code
Jun 08, 2024
Figure 1 for CERET: Cost-Effective Extrinsic Refinement for Text Generation
Figure 2 for CERET: Cost-Effective Extrinsic Refinement for Text Generation
Figure 3 for CERET: Cost-Effective Extrinsic Refinement for Text Generation
Figure 4 for CERET: Cost-Effective Extrinsic Refinement for Text Generation
Viaarxiv icon

FLAP: Flow Adhering Planning with Constrained Decoding in LLMs

Add code
Mar 09, 2024
Viaarxiv icon

Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders

Add code
Mar 07, 2024
Viaarxiv icon

Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection

Add code
Mar 06, 2024
Figure 1 for Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Figure 2 for Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Figure 3 for Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Figure 4 for Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Viaarxiv icon

MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets

Add code
Mar 05, 2024
Figure 1 for MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Figure 2 for MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Figure 3 for MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Figure 4 for MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Viaarxiv icon

Eliciting Better Multilingual Structured Reasoning from LLMs through Code

Add code
Mar 05, 2024
Viaarxiv icon