Akari Asai
Ph.D. student @ Paul G. Allen School of Computer Science & Engineering, University of Washington
Visiting Student Researcher @ Meta AI
I am currently in my fnial year of pursuing a Ph.D. in NLP at Paul G. Allen School of Computer Science & Engineering, University of Washington. I am fortunate to be advised by Prof. Hannaneh Hajishirzi. I am also spending some time at Meta AI Research as a visiting student researcher, under the supervision of Dr. Wen-tau Yih. Prior to joining UW, I obtained a B.E. in Electrical Engineering and Computer Science from The University of Tokyo, Japan.
I am on the academic job market this year! Please feel free to reach out if you’d like to discuss opportunities.
My primary research interests are centered around natural language processing and machine learning. My recent research focuses on large language models (LLMs) and Retrieval-Augmented Language Models, which address many of inherent limitations in LLMs by dynamically retrieving and incorporating external knowledge at inference time. More specifically,
-
Understanding limitations of LLMs and effectiveness of retrieval-augmented LMs – I have extensively researched the failure modes of LLMs, which scaling cannot mitigate, and was among the first to develop retrieval-augmented approaches as a solution. My work has shown their effectiveness for reducing hallucinations e.g., Adaptive Retrieval-augmented LM (ACL 2023 Oral, Best Video Award), (2) achieving more compute-efficient scaling e..g, MassiveDS (NeurIPS 2024); (3) staying updated with real-time knowledge changes e.g., Real-time QA (NeurIPS D & B 2023). I’ve co-taught the first tutorial of retrieval-augmented LMs. In our position paper, Reliable, Adaptive and Attributable LMs with Retrieval (2024) we advocate for a community shift towards retrieval-augmented LMs.
-
Developing foundations of modern retrieval-augmented LMs – I have worked to establish the foundational components of retrieval-augmented LMs, developing better architectures, training strategies, and inference techniques like Self-RAG (ICLR Oral-Top 1%, 2024), Evidentiality-guided RAG (NAACL Oral, 2022) and FAVA (COLM 2024). I’ve advanced retrieval systems to be more versatile (TART, Findings of ACL 2023), more robust to complex queries (Path Retriever, ICLR 2020)(LUKE, EMNLP 2020; 1 million downloads on HF), and more efficient (Binary Passage Retriever, ACL 2021). These methods are now integrated into major libraries like huggingface transformers, LlamaIndex and LangChain, and used in multiple real-world systems, such as COVID-19 Research Search
-
Translating state-of-the-art retrieval-augmented LMs into real-world applications – I push the boundaries of retrieval-augmented LMs by tackling real-world challenges, especially for the areas where information is more scarcely distributed. I developed the first end-to-end multilingual retrieval-augmented LM, CORA (NeurIPS 2021), and created multilingual open-retrieval datasets, including XOR QA (NAACL 2021) and AfriQA (Findings of EMNLP), covering underrepresented languages like African languages. As the lead organizer of NAACL 2022 Workshop on Multilingual Information Access, I also hosted the first cross-lingual retrieval and open-domain QA shared task. Recently, I’ve been focusing on expert domains with retrieval-augmented LMs, including code generation (CodeRAG-Bench, 2024) and scientific research.
My work has received multiple paper awards at conferences like ACL and NeurIPS workshop, and has been featured in major media outlets such as Forbes and MIT Technology Review. I’m honored to be named among the EECS Rising Stars (2024), the IBM Glable Ph.D. Fellow (2022-2023) and recognized as an MIT Technology Review Innovator Under 35 from Japan (2024).
I am also passionate about teaching, mentoring and helping students to learn research, especially students from underrepresented groups. I have been the Head TA for CSE473: Intro to AI (undergrad) and CSE599J: Data-centric ML (graduate) at UW. To reduce the barrier to start research or Ph.D. in this area, I’m hosting weekly office hours open to everyone (please sign up from Calendly!), and am a mentor for UW CSE Ph.D. Pre-Application Mentorship Service (PAMS).
Update (September 2024): I have temporarily paused my public office hours. If you’re seeking feedback on your Ph.D. application materials or have questions about the UW CSE Ph.D. program, I highly recommend applying to the UW CSE Ph.D. Pre-Application Mentorship Service (PAMS), and exploring similar programs at other institutions. Unfortunately, I won’t be able to mentor new students during the 2024-2025 academic year. If you’re interested in collaborating with students from H2Lab, please submit an inquiry through our group website’s inqury.
news
Oct 31, 2024 | I’m hornoed to be chosen as MIT Technology Review Innovators Under 35 from Japan! See the MIT Technology Review article about my work on retrieval-augmented LMs to build more reliable LM-based systems. |
---|---|
Oct 22, 2024 | We released Pangea, a new state-of-the-art multilingual and multimodal LLM! Check out our demo! |
Sep 25, 2024 | Scaling of retrieval datastore has been accepted at NeurIPS! |
Sep 19, 2024 | CopyBench has been accepted at EMNLP as a main conference paper! |
Sep 17, 2024 | I gave a lecture, “Retrieval-augmented LMs: Past, Present and Future” at CMU (Large Language Models: Methods and Applications) |
selected publications
See my full publications at the publication page!