Search Results for author: Alisa Liu

Found 22 papers, 17 papers with code

When One LLM Drools, Multi-LLM Collaboration Rules

no code implementations6 Feb 2025 Shangbin Feng, Wenxuan Ding, Alisa Liu, Zifeng Wang, Weijia Shi, Yike Wang, Zejiang Shen, Xiaochuang Han, Hunter Lang, Chen-Yu Lee, Tomas Pfister, Yejin Choi, Yulia Tsvetkov

This position paper argues that in many realistic (i. e., complex, contextualized, subjective) scenarios, one LLM is not enough to produce a reliable output.

Diversity

Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models

1 code implementation12 Aug 2024 Hila Gonen, Terra Blevins, Alisa Liu, Luke Zettlemoyer, Noah A. Smith

Despite their wide adoption, the biases and unintended behaviors of language models remain poorly understood.

Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?

1 code implementation23 Jul 2024 Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh, Noah A. Smith

Our key insight is that the ordered list of merge rules learned by a BPE tokenizer naturally reveals information about the token frequencies in its training data.

Decoding-Time Language Model Alignment with Multiple Objectives

1 code implementation27 Jun 2024 Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon S. Du

Unlike traditional methods that require careful curation of a mixture of datasets to achieve comprehensive improvement, we can quickly experiment with preference weightings using MOD to find the best combination of models.

Language Modeling Language Modelling

A Taxonomy of Ambiguity Types for NLP

no code implementations21 Mar 2024 Margaret Y. Li, Alisa Liu, Zhaofeng Wu, Noah A. Smith

Ambiguity is an critical component of language that allows for more effective communication between speakers, but is often ignored in NLP.

Tuning Language Models by Proxy

2 code implementations16 Jan 2024 Alisa Liu, Xiaochuang Han, Yizhong Wang, Yulia Tsvetkov, Yejin Choi, Noah A. Smith

Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors.

Domain Adaptation Math +2

That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?

1 code implementation23 Oct 2023 Jaechan Lee, Alisa Liu, Orevaoghene Ahia, Hila Gonen, Noah A. Smith

In experiments, we compare MT-specific models and language models for (i) their preference when given an ambiguous subsentence, (ii) their sensitivity to disambiguating context, and (iii) the performance disparity between figurative and literal source sentences.

Translation

How Language Model Hallucinations Can Snowball

1 code implementation22 May 2023 Muru Zhang, Ofir Press, William Merrill, Alisa Liu, Noah A. Smith

A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements.

Hallucination Language Modeling +3

We're Afraid Language Models Aren't Modeling Ambiguity

1 code implementation27 Apr 2023 Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A. Smith, Yejin Choi

We find that the task remains extremely challenging, including for GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset.

Sentence

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts

1 code implementation20 Dec 2022 Skyler Hallinan, Alisa Liu, Yejin Choi, Maarten Sap

Text detoxification has the potential to mitigate the harms of toxicity by rephrasing text to remove offensive meaning, but subtle toxicity remains challenging to tackle.

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

17 code implementations20 Dec 2022 Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi

Applying our method to the vanilla GPT3, we demonstrate a 33% absolute improvement over the original model on Super-NaturalInstructions, on par with the performance of InstructGPT-001, which was trained with private user data and human annotations.

Instruction Following Language Modelling

WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation

1 code implementation16 Jan 2022 Alisa Liu, Swabha Swayamdipta, Noah A. Smith, Yejin Choi

Starting with an existing dataset, MultiNLI for natural language inference (NLI), our approach uses dataset cartography to automatically identify examples that demonstrate challenging reasoning patterns, and instructs GPT-3 to compose new examples with similar patterns.

Diversity Natural Language Inference +1

Generated Knowledge Prompting for Commonsense Reasoning

1 code implementation ACL 2022 Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck, Peter West, Ronan Le Bras, Yejin Choi, Hannaneh Hajishirzi

It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models.

Language Modeling Language Modelling +1

Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach

1 code implementation23 Jun 2020 Alexander Fang, Alisa Liu, Prem Seetharaman, Bryan Pardo

Deep generative systems that learn probabilistic models from a corpus of existing music do not explicitly encode knowledge of a musical style, compared to traditional rule-based systems.

Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation

1 code implementation23 Jun 2020 Alisa Liu, Alexander Fang, Gaëtan Hadjeres, Prem Seetharaman, Bryan Pardo

In this paper, we present augmentative generation (Aug-Gen), a method of dataset augmentation for any music generation system trained on a resource-constrained domain.

Music Generation

Model selection for deep audio source separation via clustering analysis

no code implementations23 Oct 2019 Alisa Liu, Prem Seetharaman, Bryan Pardo

We compare our confidence-based ensemble approach to using individual models with no selection, to an oracle that always selects the best model and to a random model selector.

Audio Source Separation Clustering +1

CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense

1 code implementation WS 2019 Michael Chen, Mike D{'}Arcy, Alisa Liu, Fern, Jared ez, Doug Downey

To produce a more difficult dataset, we introduce a novel procedure for question acquisition in which workers author questions designed to target weaknesses of state-of-the-art neural question answering systems.

Common Sense Reasoning Question Answering +2

CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense

2 code implementations8 Apr 2019 Michael Chen, Mike D'Arcy, Alisa Liu, Jared Fernandez, Doug Downey

To produce a more difficult dataset, we introduce a novel procedure for question acquisition in which workers author questions designed to target weaknesses of state-of-the-art neural question answering systems.

 Ranked #1 on Common Sense Reasoning on CODAH (using extra training data)

Common Sense Reasoning Question Answering +2

Cannot find the paper you are looking for? You can Submit a new open access paper.