Giuseppe Carenini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Giuseppe Carenini has a total of 129 co-authors. Here are the top co-authors by number of shared publications:
- Hang Wun Raymond Li
Obstetrics and Gynaecology, School of Clinical Medicine, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, People's Republic of China
11 shared publications - Gabriel Murray
University of Fraser Valley Abbotsford BC Canada
10 shared publications - Linzi Xing
University of British Columbia
10 shared publications - Wen Xiao
University of British Columbia Vancouver BC Canada
8 shared publications - Chuyuan Li
Department of Computer Science University of British Columbia V6T 1Z4 Vancouver BC Canada
7 shared publications Chuyuan Li
Department of Computer Science γ Vancouver Stroke Program and Division of Neurology Faculty of Medicine The University of British Columbia V6T 1Z4 Vancouver BC Canada
6 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9604-9615
SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9604-9615
Open AccessSOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents
- Open Access
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Can Human Gaze Supervision Improve VLM Robustness to Misleading Data Visualizations?
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessCan Human Gaze Supervision Improve VLM Robustness to Misleading Data Visualizations?
- Open Access
Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to construct semantically-grounded soft label targets using Language Models (LMs) by projecting the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary to obtain contextually enriched supervision signals. By training the topic models to reconstruct the soft labels using the LM hidden states, our method produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Experiments on three datasets show that our method achieves substantial improvements in topic coherence, purity over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications.
Open AccessImproving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to construct semantically-grounded soft label targets using Language Models (LMs) by projecting the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary to obtain contextually enriched supervision signals. By training the topic models to reconstruct the soft labels using the LM hidden states, our method produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Experiments on three datasets show that our method achieves substantial improvements in topic coherence, purity over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications.
- Open Access
ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement
Charts are a crucial visual medium for communicating and representing information. While Large Vision-Language Models (LVLMs) have made progress on chart question answering (CQA), the task remains challenging, particularly when models attend to irrelevant regions of the chart. In this work, we present ChartGaze, a new eye-tracking dataset that captures human gaze patterns during chart reasoning tasks. Through a systematic comparison of human and model attention, we find that LVLMs often diverge from human gaze, leading to reduced interpretability and accuracy. To address this, we propose a gaze-guided attention refinement that aligns image-text attention with human fixations. Our approach improves both answer accuracy and attention alignment, yielding gains of up to 2.56 percentage points across multiple models. These results demonstrate the promise of incorporating human gaze to enhance both the reasoning quality and interpretability of chart-focused LVLMs.
Open AccessChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement
Charts are a crucial visual medium for communicating and representing information. While Large Vision-Language Models (LVLMs) have made progress on chart question answering (CQA), the task remains challenging, particularly when models attend to irrelevant regions of the chart. In this work, we present ChartGaze, a new eye-tracking dataset that captures human gaze patterns during chart reasoning tasks. Through a systematic comparison of human and model attention, we find that LVLMs often diverge from human gaze, leading to reduced interpretability and accuracy. To address this, we propose a gaze-guided attention refinement that aligns image-text attention with human fixations. Our approach improves both answer accuracy and attention alignment, yielding gains of up to 2.56 percentage points across multiple models. These results demonstrate the promise of incorporating human gaze to enhance both the reasoning quality and interpretability of chart-focused LVLMs.
- Open Access
Delta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer's Disease Detection
Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that leads to dementia, and early intervention can greatly benefit from analyzing linguistic abnormalities. In this work, we explore the potential of Large Language Models (LLMs) as health assistants for AD diagnosis from patient-generated text using in-context learning (ICL), where tasks are defined through a few input-output examples. Empirical results reveal that conventional ICL methods, such as similarity-based selection, perform poorly for AD diagnosis, likely due to the inherent complexity of this task. To address this, we introduce Delta-KNN, a novel demonstration selection strategy that enhances ICL performance. Our method leverages a delta score to assess the relative gains of each training example, coupled with a KNN-based retriever that dynamically selects optimal "representatives" for a given input. Experiments on two AD detection datasets across three open-source LLMs demonstrate that Delta-KNN consistently outperforms existing ICL baselines. Notably, when using the Llama-3.1 model, our approach achieves new state-of-the-art results, surpassing even supervised classifiers.
Open AccessDelta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer's Disease Detection
Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that leads to dementia, and early intervention can greatly benefit from analyzing linguistic abnormalities. In this work, we explore the potential of Large Language Models (LLMs) as health assistants for AD diagnosis from patient-generated text using in-context learning (ICL), where tasks are defined through a few input-output examples. Empirical results reveal that conventional ICL methods, such as similarity-based selection, perform poorly for AD diagnosis, likely due to the inherent complexity of this task. To address this, we introduce Delta-KNN, a novel demonstration selection strategy that enhances ICL performance. Our method leverages a delta score to assess the relative gains of each training example, coupled with a KNN-based retriever that dynamically selects optimal "representatives" for a given input. Experiments on two AD detection datasets across three open-source LLMs demonstrate that Delta-KNN consistently outperforms existing ICL baselines. Notably, when using the Llama-3.1 model, our approach achieves new state-of-the-art results, surpassing even supervised classifiers.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 17-30
Hierarchical Attention Adapter for Abstractive Dialogue Summarization
Raymond Li, Chuyuan Li, Gabriel Murray, Giuseppe Carenini. Proceedings of The 5th New Frontiers in Summarization Workshop. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 17-30
Open AccessHierarchical Attention Adapter for Abstractive Dialogue Summarization
Raymond Li, Chuyuan Li, Gabriel Murray, Giuseppe Carenini. Proceedings of The 5th New Frontiers in Summarization Workshop. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 12104-12124
ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement
Ali Salamatian, Amirhossein Abaskohi, Wan-Cyuan Fan, Mir Rayat Imtiaz Hossain, Leonid Sigal, Giuseppe Carenini. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 12104-12124
Open AccessChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement
Ali Salamatian, Amirhossein Abaskohi, Wan-Cyuan Fan, Mir Rayat Imtiaz Hossain, Leonid Sigal, Giuseppe Carenini. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 135-156
Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
Juntai Cao, Xiang Zhang, Raymond Li, Jiaqi Wei, Chuyuan Li, Shafiq Joty, Giuseppe Carenini. Proceedings of The 5th New Frontiers in Summarization Workshop. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 135-156
Open AccessMulti2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
Juntai Cao, Xiang Zhang, Raymond Li, Jiaqi Wei, Chuyuan Li, Shafiq Joty, Giuseppe Carenini. Proceedings of The 5th New Frontiers in Summarization Workshop. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 148-156
Discourse Relation Recognition with Language Models Under Different Data Availability
Shuhaib Mehri, Chuyuan Li, Giuseppe Carenini. Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 148-156
Open AccessDiscourse Relation Recognition with Language Models Under Different Data Availability
Shuhaib Mehri, Chuyuan Li, Giuseppe Carenini. Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 11686-11703
CEMTM: Contextual Embedding-based Multimodal Topic Modeling
Amirhossein Abaskohi, Raymond Li, Chuyuan Li, Shafiq Joty, Giuseppe Carenini. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 11686-11703
Open AccessCEMTM: Contextual Embedding-based Multimodal Topic Modeling
Amirhossein Abaskohi, Raymond Li, Chuyuan Li, Shafiq Joty, Giuseppe Carenini. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.