Hannaneh Hajishirzi

Hannaneh Hajishirzi

Auto-generated profile, based on publicly available information

Hannaneh Hajishirzi

University of Washington

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 January 2023
Verified
Conference Paper
Open access
PDF file
SMSewon Min
Sewon Min
KKKalpesh Krishna
Kalpesh Krishna
XLXinxi Lyu
Xinxi Lyu
MLMike Lewis
Mike Lewis
WYWen-Tau Yih
Wen-Tau Yih
HHHannaneh Hajishirzi
Hannaneh Hajishirzi
Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, Hannaneh Hajishirzi. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

1 January 2019
Verified
Conference Paper
Open access
PDF file
AAAida Amini
Aida Amini
SGSaadia Gabriel
Saadia Gabriel
SLShanchuan Lin
Shanchuan Lin
RKRik Koncel-Kedziorski
Rik Koncel-Kedziorski
YCYejin Choi
Yejin Choi
HHHannaneh Hajishirzi
Hannaneh Hajishirzi
Aida Amini, Saadia Gabriel, Shanchuan Lin, Rik Koncel-Kedziorski, Yejin Choi, Hannaneh Hajishirzi. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.

1 January 2023
Verified
Conference Paper
Open access
PDF file
XLXinxi Lyu
Xinxi Lyu
SMSewon Min
Sewon Min
IBIz Beltagy
Iz Beltagy
LZLuke Zettlemoyer
Luke Zettlemoyer
HHHannaneh Hajishirzi
Hannaneh Hajishirzi
Xinxi Lyu, Sewon Min, Iz Beltagy, Luke Zettlemoyer, Hannaneh Hajishirzi. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

4 February 2026 in Nature
Verified
Journal Article
Open access
PDF file
AAAkari Asai
Akari Asai
JHJacqueline He
Jacqueline He
RSRulin Shao
Rulin Shao
WSWeijia Shi
Weijia Shi
ASAmanpreet Singh
Amanpreet Singh
HHHannaneh Hajishirzi
Hannaneh Hajishirzi
Scientific progress depends on the ability of researchers to synthesize the growing body of literature. Can large language models (LLMs) assist scientists in this task? Here we introduce OpenScholar, a specialized retrieval-augmented language model (LM)1 that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscience and biomedicine. Despite being a smaller open model, OpenScholar-8B outperforms GPT-4o by 6.1% and PaperQA2 by 5.5% in correctness on a challenging multi-paper synthesis task from the new ScholarQABench. Although GPT-4o hallucinates citations 78–90% of the time, OpenScholar achieves citation accuracy on par with human experts. OpenScholar’s data store, retriever and self-feedback inference loop improve off-the-shelf LMs: for instance, OpenScholar-GPT-4o improves the correctness of GPT-4o by 12%. In human evaluations, experts preferred OpenScholar-8B and OpenScholar-GPT-4o responses over expert-written ones 51% and 70% of the time, respectively, compared with 32% for GPT-4o. We open-source all artefacts, including our code, models, data store, datasets and a public demo.

17 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
AAAkari Asai
Akari Asai
ZWZeqiu Wu
Zeqiu Wu
YWYizhong Wang
Yizhong Wang
ASAvirup Sil
Avirup Sil
HHHannaneh Hajishirzi
Hannaneh Hajishirzi
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad hoc approach that augments LMs with retrieval of relevant knowledge, decreases such issues. However, indiscriminately retrieving and incorporating a fixed number of retrieved passages, regardless of whether retrieval is necessary, or passages are relevant, diminishes LM versatility or can lead to unhelpful response generation. We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) that enhances an LM's quality and factuality through retrieval and self-reflection. Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens. Generating reflection tokens makes the LM controllable during the inference phase, enabling it to tailor its behavior to diverse task requirements. Experiments show that Self-RAG (7B and 13B parameters) significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks. Specifically, Self-RAG outperforms ChatGPT and retrieval-augmented Llama2-chat on Open-domain QA, reasoning and fact verification tasks, and it shows significant gains in improving factuality and citation accuracy for long-form generations relative to these models.

2 December 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SMSachin Mehta
Sachin Mehta
HHHannaneh Hajishirzi
Hannaneh Hajishirzi
MRMohammad Rastegari
Mohammad Rastegari
We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply lightweight convolutional filtering across each dimension of the input tensor while dimension-wise fusion efficiently combines these dimension-wise representations; allowing the DiCE unit to efficiently encode spatial and channel-wise information contained in the input tensor. The DiCE unit is simple and can be seamlessly integrated with any architecture to improve its efficiency and performance. Compared to depth-wise separable convolutions, the DiCE unit shows significant improvements across different architectures. When DiCE units are stacked to build the DiCENet model, we observe significant improvements over state-of-the-art models across various computer vision tasks including image classification, object detection, and semantic segmentation. On the ImageNet dataset, the DiCENet delivers 2-4% higher accuracy than state-of-the-art manually designed models (e.g., MobileNetv2 and ShuffleNetv2). Also, DiCENet generalizes better to tasks (e.g., object detection) that are often used in resource-constrained devices in comparison to state-of-the-art separable convolution-based efficient networks, including neural search-based methods (e.g., MobileNetv3 and MixNet).