Saab Mansour
Saab Mansour has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
Yi Zhang
University AWS AI Labs
8 shared publicationsHang Su
AWS AI Labs
7 shared publications- Sailik Sengupta
AI Labs WS
7 shared publications - Igor Shalyminov
Korea Advanced Institute of Science & Technology AWS AI Labs ♡ The University of Texas at Austin
6 shared publications - Daniele Bonadiman
AI Labs WS
5 shared publications - Arshit Gupta
AI Labs WS
4 shared publications
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 143-159
PAARS: Persona Aligned Agentic Retail Shoppers
Saab Mansour, Leonardo Perelli, Lorenzo Mainetti, George Davidson, Stefano D’Amato. Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 143-159
Open AccessPAARS: Persona Aligned Agentic Retail Shoppers
Saab Mansour, Leonardo Perelli, Lorenzo Mainetti, George Davidson, Stefano D’Amato. Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025). 2025.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26280-26300
DeAL: Decoding-time Alignment for Large Language Models
James Y. Huang, Sailik Sengupta, Daniele Bonadiman, Yi-An Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, Dan Roth. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26280-26300
Top Cited PapersOpen AccessDeAL: Decoding-time Alignment for Large Language Models
James Y. Huang, Sailik Sengupta, Daniele Bonadiman, Yi-An Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, Dan Roth. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
Structured List-Grounded Question Answering
Document-grounded dialogue systems aim to answer user queries by leveraging external information. Previous studies have mainly focused on handling free-form documents, often overlooking structured data such as lists, which can represent a range of nuanced semantic relations. Motivated by the observation that even advanced language models like GPT-3.5 often miss semantic cues from lists, this paper aims to enhance question answering (QA) systems for better interpretation and use of structured lists. To this end, we introduce the LIST2QA dataset, a novel benchmark to evaluate the ability of QA systems to respond effectively using list information. This dataset is created from unlabeled customer service documents using language models and model-based filtering processes to enhance data quality, and can be used to fine-tune and evaluate QA models. Apart from directly generating responses through fine-tuned models, we further explore the explicit use of Intermediate Steps for Lists (ISL), aligning list items with user backgrounds to better reflect how humans interpret list items before generating responses. Our experimental results demonstrate that models trained on LIST2QA with our ISL approach outperform baselines across various metrics. Specifically, our fine-tuned Flan-T5-XL model shows increases of 3.1% in ROUGE-L, 4.6% in correctness, 4.5% in faithfulness, and 20.6% in completeness compared to models without applying filtering and the proposed ISL method.
Open AccessStructured List-Grounded Question Answering
Document-grounded dialogue systems aim to answer user queries by leveraging external information. Previous studies have mainly focused on handling free-form documents, often overlooking structured data such as lists, which can represent a range of nuanced semantic relations. Motivated by the observation that even advanced language models like GPT-3.5 often miss semantic cues from lists, this paper aims to enhance question answering (QA) systems for better interpretation and use of structured lists. To this end, we introduce the LIST2QA dataset, a novel benchmark to evaluate the ability of QA systems to respond effectively using list information. This dataset is created from unlabeled customer service documents using language models and model-based filtering processes to enhance data quality, and can be used to fine-tune and evaluate QA models. Apart from directly generating responses through fine-tuned models, we further explore the explicit use of Intermediate Steps for Lists (ISL), aligning list items with user backgrounds to better reflect how humans interpret list items before generating responses. Our experimental results demonstrate that models trained on LIST2QA with our ISL approach outperform baselines across various metrics. Specifically, our fine-tuned Flan-T5-XL model shows increases of 3.1% in ROUGE-L, 4.6% in correctness, 4.5% in faithfulness, and 20.6% in completeness compared to models without applying filtering and the proposed ISL method.
- Open Access
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models. While addressing label noise, previous works on semi-supervised learning primarily focus on natural language understanding tasks, assuming each sample has a unique label. However, these methods are not directly applicable to SSDS, as it is a generative task, and each dialogue can be summarized in different ways. In this work, we propose a novel scoring approach, SiCF, which encapsulates three primary dimensions of summarization model quality: Semantic invariance (indicative of model confidence), Coverage (factual recall), and Faithfulness (factual precision). Using the SiCF score, we select unlabeled dialogues with high-quality generated summaries to train summarization models. Comprehensive experiments on three public datasets demonstrate the effectiveness of SiCF scores in uncertainty estimation and semi-supervised learning for dialogue summarization tasks. Our code is available at \url{https://github.com/amazon-science/summarization-sicf-score}.
Open AccessSemi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models. While addressing label noise, previous works on semi-supervised learning primarily focus on natural language understanding tasks, assuming each sample has a unique label. However, these methods are not directly applicable to SSDS, as it is a generative task, and each dialogue can be summarized in different ways. In this work, we propose a novel scoring approach, SiCF, which encapsulates three primary dimensions of summarization model quality: Semantic invariance (indicative of model confidence), Coverage (factual recall), and Faithfulness (factual precision). Using the SiCF score, we select unlabeled dialogues with high-quality generated summaries to train summarization models. Comprehensive experiments on three public datasets demonstrate the effectiveness of SiCF scores in uncertainty estimation and semi-supervised learning for dialogue summarization tasks. Our code is available at \url{https://github.com/amazon-science/summarization-sicf-score}.
- Top Cited PapersOpen Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 906-922
FineSurE: Fine-grained Summarization Evaluation using LLMs
Hwanjun Song, Hang Su, Igor Shalyminov, Jason Cai, Saab Mansour. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 906-922
Top Cited PapersOpen AccessFineSurE: Fine-grained Summarization Evaluation using LLMs
Hwanjun Song, Hang Su, Igor Shalyminov, Jason Cai, Saab Mansour. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 552-567
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders
Yuwei Zhang, Siffi Singh, Sailik Sengupta, Igor Shalyminov, Hang Su, Hwanjun Song, Saab Mansour. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 552-567
Open AccessCan Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders
Yuwei Zhang, Siffi Singh, Sailik Sengupta, Igor Shalyminov, Hang Su, Hwanjun Song, Saab Mansour. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5154-5169
Eliciting Better Multilingual Structured Reasoning from LLMs through Code
Bryan Li, Tamer Alkhouli, Daniele Bonadiman, Nikolaos Pappas, Saab Mansour. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5154-5169
Open AccessEliciting Better Multilingual Structured Reasoning from LLMs through Code
Bryan Li, Tamer Alkhouli, Daniele Bonadiman, Nikolaos Pappas, Saab Mansour. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5976-5996
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Jianfeng He, Hang Su, Jason Cai, Igor Shalyminov, Hwanjun Song, Saab Mansour. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5976-5996
Open AccessSemi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Jianfeng He, Hang Su, Jason Cai, Igor Shalyminov, Hwanjun Song, Saab Mansour. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 517-539
FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs
Shamik Roy, Sailik Sengupta, Daniele Bonadiman, Saab Mansour, Arshit Gupta. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 517-539
Open AccessFLAP: Flow-Adhering Planning with Constrained Decoding in LLMs
Shamik Roy, Sailik Sengupta, Daniele Bonadiman, Saab Mansour, Arshit Gupta. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 7377-7390
CERET: Cost-Effective Extrinsic Refinement for Text Generation
Jason Cai, Hang Su, Monica Sunkara, Igor Shalyminov, Saab Mansour. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 7377-7390
Open AccessCERET: Cost-Effective Extrinsic Refinement for Text Generation
Jason Cai, Hang Su, Monica Sunkara, Igor Shalyminov, Saab Mansour. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.