Nedim Lipka
Nedim Lipka has a total of 107 co-authors. Here are the top co-authors by number of shared publications:
- Ryan Anthony Rossi
Adobe Research, San Jose, USA
17 shared publications - Franck Dernoncourt
Adobe Research
10 shared publications - Alexa Siu
Adobe Research, San Jose, California, USA
8 shared publications - Sungchul Kim
Institute for Global Rare Disease Network, Professional Graduate School of Korean Medicine, Wonkwang University, Iksan 54538, Republic of Korea
7 shared publications - Alexa Siu
Adobe Research
4 shared publications - Franck Dernoncourt
Adobe Research 801 N 34th St 98103 Seattle WA USA
4 shared publications
Latest Publications
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1216-1220
Knowledge Homophily in Large Language Models
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1216-1220
Open AccessKnowledge Homophily in Large Language Models
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 663-672
Few-shot Fine-grained Image Classification with Interpretable Prompt Learning through Distribution Alignment
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 663-672
Open AccessFew-shot Fine-grained Image Classification with Interpretable Prompt Learning through Distribution Alignment
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1167-1171
Personalizing Data Delivery: Investigating User Characteristics and Enhancing LLM Predictions
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1167-1171
Open AccessPersonalizing Data Delivery: Investigating User Characteristics and Enhancing LLM Predictions
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
DocVoyager: Anticipating User’s Information Needs and Guiding Document Reading through Question Answering
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessDocVoyager: Anticipating User’s Information Needs and Guiding Document Reading through Question Answering
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 9818-9832
LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles
Ho Yin Sam Ng, Edward Hsu, Aashish Anantha Ramakrishnan, Branislav Kveton, Nedim Lipka, Franck Dernoncourt, Dongwon Lee, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ting-Hao Kenneth Huang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 9818-9832
Open AccessLaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles
Ho Yin Sam Ng, Edward Hsu, Aashish Anantha Ramakrishnan, Branislav Kveton, Nedim Lipka, Franck Dernoncourt, Dongwon Lee, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ting-Hao Kenneth Huang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18306-18321
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, Yu Wang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18306-18321
Open AccessMixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, Yu Wang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
Survey of User Interface Design and Interaction Techniques in Generative AI Applications
The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it lacks specificity regarding the user interface designs and patterns used to create these applications. Therefore, we present a survey that comprehensively presents taxonomies of how a human interacts with AI and the user interaction patterns designed to meet the needs of a variety of relevant use cases. We focus primarily on user-guided interactions, surveying interactions that are initiated by the user and do not include any implicit signals given by the user. With this survey, we aim to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. In doing so, we also strive to lower the entry barrier for those attempting to learn more about the design of generative AI applications.
Open AccessSurvey of User Interface Design and Interaction Techniques in Generative AI Applications
The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it lacks specificity regarding the user interface designs and patterns used to create these applications. Therefore, we present a survey that comprehensively presents taxonomies of how a human interacts with AI and the user interaction patterns designed to meet the needs of a variety of relevant use cases. We focus primarily on user-guided interactions, surveying interactions that are initiated by the user and do not include any implicit signals given by the user. With this survey, we aim to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. In doing so, we also strive to lower the entry barrier for those attempting to learn more about the design of generative AI applications.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2442-2452
Topology-aware Retrieval Augmentation for Text Generation
Retrieval-augmented Generation has been used to augment Language Models by retrieving texts from external databases. Since real-world texts are often connected in the graph (e.g., papers in citation networks), we use these relations to guide the retrieval process of RAG. Concretely, we investigate proximity and role-based relations, where the former considers topologically close nodes and the latter considers structurally similar nodes. We empirically verify their correlation to text relations, which motivates us to propose the framework of Topology-aware Retrieval-augmented Generation for text generation, which consists of a retrieval module to retrieve texts by their topological relations and an aggregation module to compose retrieved texts into prompts triggering LLMs for text generation. Extensive experiments verify the effectiveness of this framework, signifying the potential of equipping RAG with topological awareness.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2442-2452
Open AccessTopology-aware Retrieval Augmentation for Text Generation
Retrieval-augmented Generation has been used to augment Language Models by retrieving texts from external databases. Since real-world texts are often connected in the graph (e.g., papers in citation networks), we use these relations to guide the retrieval process of RAG. Concretely, we investigate proximity and role-based relations, where the former considers topologically close nodes and the latter considers structurally similar nodes. We empirically verify their correlation to text relations, which motivates us to propose the framework of Topology-aware Retrieval-augmented Generation for text generation, which consists of a retrieval module to retrieve texts by their topological relations and an aggregation module to compose retrieved texts into prompts triggering LLMs for text generation. Extensive experiments verify the effectiveness of this framework, signifying the potential of equipping RAG with topological awareness.
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Marco: Supporting Business Document Workflows via Collection-Centric Information Foraging with Large Language Models
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessMarco: Supporting Business Document Workflows via Collection-Centric Information Foraging with Large Language Models
- Open Access
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Thinking Outside the Box: Non-Designer Perspectives and Recommendations for Template-Based Graphic Design Tools
Many digital graphic design tools provide design templates to help non-designers quickly get started. Users often have assets (e.g. images and text) that they want to incorporate when starting their design. Existing interaction schemes may be insufficient to help users adapt a template to work with their assets and hinder their sense of creativity and productivity. To investigate the effects of templates on non-designer workflows, we conducted a think-aloud design study (N=10) where participants designed posters using one or more templates, followed by semi-structured interviews. Our findings show that while templates help users converge to a final design quickly and partially alleviate the need for tedious decision-making, they may also lead to fixation and frustration when interactions do not support divergent thinking and flexible editing. We present design recommendations for creativity support tools (CSTs) that make use of templates, to address non-designers’ creative and practical needs.
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessThinking Outside the Box: Non-Designer Perspectives and Recommendations for Template-Based Graphic Design Tools
Many digital graphic design tools provide design templates to help non-designers quickly get started. Users often have assets (e.g. images and text) that they want to incorporate when starting their design. Existing interaction schemes may be insufficient to help users adapt a template to work with their assets and hinder their sense of creativity and productivity. To investigate the effects of templates on non-designer workflows, we conducted a think-aloud design study (N=10) where participants designed posters using one or more templates, followed by semi-structured interviews. Our findings show that while templates help users converge to a final design quickly and partially alleviate the need for tedious decision-making, they may also lead to fixation and frustration when interactions do not support divergent thinking and flexible editing. We present design recommendations for creativity support tools (CSTs) that make use of templates, to address non-designers’ creative and practical needs.