Alexa Siu

Alexa Siu

Auto-generated profile, based on publicly available information

Alexa Siu

Adobe Research

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YWYu Wang
Yu Wang
NLNedim Lipka
Nedim Lipka
RRRyan Rossi
Ryan Rossi
ASAlexa Siu
Alexa Siu
RZRuiyi Zhang
Ruiyi Zhang
TDTyler Derr
Tyler Derr
The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design and retrieval augmented generation for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA.

1 January 2024
Verified
Conference Paper
Open access
PDF file
JSJon Saad-Falcon
Jon Saad-Falcon
JBJoe Barrow
Joe Barrow
ASAlexa Siu
Alexa Siu
ANAni Nenkova
Ani Nenkova
SYSeunghyun Yoon
Seunghyun Yoon
FDFranck Dernoncourt
Franck Dernoncourt
Jon Saad-Falcon, Joe Barrow, Alexa Siu, Ani Nenkova, Seunghyun Yoon, Ryan A. Rossi, Franck Dernoncourt. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2024.

1 January 2024
Verified
Conference Paper
Open access
PDF file
PMPuneet Mathur
Puneet Mathur
ASAlexa Siu
Alexa Siu
NLNedim Lipka
Nedim Lipka
TSTong Sun
Tong Sun
Puneet Mathur, Alexa Siu, Nedim Lipka, Tong Sun. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2024.

1 January 2024
Verified
Conference Paper
Open access
PDF file
PMPuneet Mathur
Puneet Mathur
ASAlexa Siu
Alexa Siu
VMVarun Manjunatha
Varun Manjunatha
TSTong Sun
Tong Sun
Puneet Mathur, Alexa Siu, Varun Manjunatha, Tong Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2024.

29 October 2024 in arXiv
Verified
Preprint
Open access
PDF file
RLReuben Luera
Reuben Luera
RRRyan Rossi
Ryan Rossi
ASAlexa Siu
Alexa Siu
FDFranck Dernoncourt
Franck Dernoncourt
TYTong Yu
Tong Yu
NLNedim Lipka
Nedim Lipka
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.

25 December 2023 in arXiv
Verified
Preprint
Open access
PDF file
YWYu Wang
Yu Wang
NLNedim Lipka
Nedim Lipka
RRRyan Rossi
Ryan Rossi
ASAlexa Siu
Alexa Siu
RZRuiyi Zhang
Ruiyi Zhang
TDTyler Derr
Tyler Derr
The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in the scenario of multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of different documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or intra-document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA.