PaperMetrixEvidence-aware discovery
TR
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Hannaneh Hajishirzi

28 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

    2019 · arXiv (Cornell University)

    We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or …

  2. DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling

    2019 · arXiv (Cornell University)

    For sequence models with large vocabularies, a majority of network parameters lie in the input and output layers. In this work, we describe a new method, DeFINE, for learning deep token representations efficiently. Our architecture …

  3. Aligning to Social Norms and Values in Interactive Narratives

    2022 · arXiv (Cornell University)

    We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games -- environments wherein an agent perceives and interacts with a world through natural language. …

  4. Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

    2022 · arXiv (Cornell University)

    We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework. However, …

  5. Self-Instruct: Aligning Language Models with Self-Generated Instructions

    2022 · arXiv (Cornell University)

    Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is often limited in quantity, …

  6. ART: Automatic multi-step reasoning and tool-use for large language models

    2023 · arXiv (Cornell University)

    Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning step can rely on external tools to support computation beyond …

  7. Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

    2023 · arXiv (Cornell University)

    Since the release of TÜLU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques. We test and incorporate a number of these advances into …

  8. SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature

    2024 · arXiv (Cornell University)

    We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks. These tasks span five core scientific literature understanding capabilities: information extraction, summarization, question …

  9. 2 OLMo 2 Furious

    2024 · arXiv (Cornell University)

    We present OLMo 2, the next generation of our fully open language models. OLMo 2 includes a family of dense autoregressive language models at 7B, 13B and 32B scales with fully released artifacts -- model …

  10. OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

    2025 · arXiv (Cornell University)

    We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches between segments of language model output …

  11. Parsing Algebraic Word Problems into Equations

    2015 · Transactions of the Association for Computational Linguistics

    This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees and score their likelihood by learning local …

  12. Learning Knowledge Graphs for Question Answering through Conversational Dialog

    2015

    We describe how a question-answering system can learn about its domain from conversational dialogs. Our system learns to relate concepts in science questions to propositions in a fact corpus, stores new concepts and relations in …

  13. MAWPS: A Math Word Problem Repository

    2016

    Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, Hannaneh Hajishirzi. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

  14. Bidirectional Attention Flow for Machine Comprehension

    2016 · arXiv (Cornell University)

    Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention …

  15. A general framework for information extraction using dynamic span graphs

    2019

    Yi Luan, Dave Wadden, Luheng He, Amy Shah, Mari Ostendorf, 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 …

  16. Multi-hop Reading Comprehension through Question Decomposition and Rescoring

    2019

    Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop RC models. …

  17. Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

    2019

    Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query, which is computationally prohibitive. In this paper, we introduce query-agnostic …

  18. Compositional Questions Do Not Necessitate Multi-hop Reasoning

    2019

    Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC datasets. For example, even highly compositional questions …

  19. A Discrete Hard EM Approach for Weakly Supervised Question Answering

    2019

    Sewon Min, Danqi Chen, Hannaneh Hajishirzi, Luke Zettlemoyer. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

  20. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

    2019 · arXiv (Cornell University)

    Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question. This paper introduces a new graph-based recurrent retrieval approach …

  21. Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

    2020 · arXiv (Cornell University)

    Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random seeds can lead to …

  22. A Controllable Model of Grounded Response Generation

    2021 · Proceedings of the AAAI Conference on Artificial Intelligence

    Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses. Attempts to boost informativeness alone come at the expense of factual accuracy, …

  23. AmbigQA: Answering Ambiguous Open-domain Questions

    2020

    Ambiguity is inherent to open-domain question answering; especially when exploring new topics, it can be difficult to ask questions that have a single, unambiguous answer. In this paper, we introduce AMBIGQA, a new open-domain question …

  24. Noisy Channel Language Model Prompting for Few-Shot Text Classification

    2021 · arXiv (Cornell University)

    We introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel models compute the conditional probability …

  25. MetaICL: Learning to Learn In Context

    2021 · arXiv (Cornell University)

    We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training enables …

  26. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

    2022

    Large language models (LMs) are able to in-context learn—perform a new task via inference alone by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs. However, there has been little understanding …

  27. Self-Instruct: Aligning Language Models with Self-Generated Instructions

    2023

    Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

  28. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

    2023

    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.