Search Results - "Phang, Jason"

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization by Shen, Yiqiu, Wu, Nan, Phang, Jason, Park, Jungkyu, Liu, Kangning, Tyagi, Sudarshini, Heacock, Laura, Kim, S. Gene, Moy, Linda, Cho, Kyunghyun, Geras, Krzysztof J.

“…•We propose a novel neural network model for screening mammography interpretation•Our model outperforms popular models such as ResNet-34 and Faster R-CNN•Our…”
Get full text

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening by Wu, Nan, Phang, Jason, Park, Jungkyu, Shen, Yiqiu, Huang, Zhe, Zorin, Masha, Jastrzebski, Stanislaw, Fevry, Thibault, Katsnelson, Joe, Kim, Eric, Wolfson, Stacey, Parikh, Ujas, Gaddam, Sushma, Lin, Leng Leng Young, Ho, Kara, Weinstein, Joshua D., Reig, Beatriu, Gao, Yiming, Toth, Hildegard, Pysarenko, Kristine, Lewin, Alana, Lee, Jiyon, Airola, Krystal, Mema, Eralda, Chung, Stephanie, Hwang, Esther, Samreen, Naziya, Kim, S. Gene, Heacock, Laura, Moy, Linda, Cho, Kyunghyun, Geras, Krzysztof J.

“…We present a deep convolutional neural network for breast cancer screening exam classification, trained, and evaluated on over 200000 exams (over 1000000…”
Get full text

Investigating the Effectiveness of HyperTuning via Gisting by Phang, Jason

“…Gisting (Mu et al., 2023) is a simple method for training models to compress information into fewer token representations using a modified attention mask, and…”
Get full text

Reducing False-Positive Biopsies using Deep Neural Networks that Utilize both Local and Global Image Context of Screening Mammograms by Wu, Nan, Huang, Zhe, Shen, Yiqiu, Park, Jungkyu, Phang, Jason, Makino, Taro, Gene Kim, S., Cho, Kyunghyun, Heacock, Laura, Moy, Linda, Geras, Krzysztof J.

“…Breast cancer is the most common cancer in women, and hundreds of thousands of unnecessary biopsies are done around the world at a tremendous cost. It is…”
Get full text

Investigating Efficiently Extending Transformers for Long Input Summarization by Phang, Jason, Zhao, Yao, Liu, Peter J

“…While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a…”
Get full text

Unsupervised Sentence Compression using Denoising Auto-Encoders by Févry, Thibault, Phang, Jason

“…In sentence compression, the task of shortening sentences while retaining the original meaning, models tend to be trained on large corpora containing pairs of…”
Get full text

Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers by Phang, Jason, Liu, Haokun, Bowman, Samuel R

“…Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly…”
Get full text

HyperTuning: Toward Adapting Large Language Models without Back-propagation by Phang, Jason, Mao, Yi, He, Pengcheng, Chen, Weizhu

“…Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require…”
Get full text

Large Language Models as Misleading Assistants in Conversation by Hou, Betty Li, Shi, Kejian, Phang, Jason, Aung, James, Adler, Steven, Campbell, Rosie

“…Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether…”
Get full text

EleutherAI: Going Beyond "Open Science" to "Science in the Open" by Phang, Jason, Bradley, Herbie, Gao, Leo, Castricato, Louis, Biderman, Stella

“…Over the past two years, EleutherAI has established itself as a radically novel initiative aimed at both promoting open-source research and conducting research…”
Get full text

Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability by Phang, Jason, Park, Jungkyu, Geras, Krzysztof J

“…Saliency maps that identify the most informative regions of an image for a classifier are valuable for model interpretability. A common approach to creating…”
Get full text

Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data? by Tang, Xiangru, Zong, Yiming, Phang, Jason, Zhao, Yilun, Zhou, Wangchunshu, Cohan, Arman, Gerstein, Mark

“…Despite the remarkable capabilities of Large Language Models (LLMs) like GPT-4, producing complex, structured tabular data remains challenging. Our study…”
Get full text

Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair by Phang, Jason, Chen, Angelica, Huang, William, Bowman, Samuel R

“…More capable language models increasingly saturate existing task benchmarks, in some cases outperforming humans. This has left little headroom with which to…”
Get full text

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs by Chen, Angelica, Phang, Jason, Parrish, Alicia, Padmakumar, Vishakh, Zhao, Chen, Bowman, Samuel R, Cho, Kyunghyun

“…Transactions on Machine Learning Research (2024) Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but…”
Get full text

Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions by Parrish, Alicia, Trivedi, Harsh, Nangia, Nikita, Padmakumar, Vishakh, Phang, Jason, Saimbhi, Amanpreet Singh, Bowman, Samuel R

“…The use of language-model-based question-answering systems to aid humans in completing difficult tasks is limited, in part, by the unreliability of the text…”
Get full text

SQuALITY: Building a Long-Document Summarization Dataset the Hard Way by Wang, Alex, Pang, Richard Yuanzhe, Chen, Angelica, Phang, Jason, Bowman, Samuel R

“…Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with…”
Get full text

Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions by Parrish, Alicia, Trivedi, Harsh, Perez, Ethan, Chen, Angelica, Nangia, Nikita, Phang, Jason, Bowman, Samuel R

“…Current QA systems can generate reasonable-sounding yet false answers without explanation or evidence for the generated answer, which is especially problematic…”
Get full text

Pretraining Language Models with Human Preferences by Korbak, Tomasz, Shi, Kejian, Chen, Angelica, Bhalerao, Rasika, Buckley, Christopher L, Phang, Jason, Bowman, Samuel R, Perez, Ethan

“…Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods,…”
Get full text

Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks by Phang, Jason, Févry, Thibault, Bowman, Samuel R

“…Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding…”
Get full text

Do Attention Heads in BERT Track Syntactic Dependencies? by Htut, Phu Mon, Phang, Jason, Bordia, Shikha, Bowman, Samuel R

“…We investigate the extent to which individual attention heads in pretrained transformer language models, such as BERT and RoBERTa, implicitly capture syntactic…”
Get full text