21 citations · 66 across the 26 of their papers we have counts for
30 papers
Generating Edit-Inducing Questions for AI Research Manuscripts
Sebastian Joseph, Zichao Wang, Jennifer Healey +3
We study the ability of LLMs to generate edit-inducing questions whose answer will improve a paper draft. On a dataset of paired submission and camera-ready papers from ICLR and Ne…
LinkNav: Surfacing Interconnected Information in Scientific Articles
Sebastian Joseph, Jennifer Healey, Junyi Jessy Li +1
We present LinkNav, an enhanced experience for reading academic papers which makes explicit connections between related but non-adjacent passages. To create the experience, we inst…
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
Jiacheng Shi, Hongfei Du, Xinyuan Song +3
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acousti…
SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps
Neha Srikanth, Victor Bursztyn, Puneet Mathur +1
We introduce SQLSpace, a human-interpretable, generalizable, compact representation for text-to-SQL examples derived with minimal human intervention. We demonstrate the utility of…
SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
Shengcao Cao, Jiuxiang Gu, Jason Kuen +7
Open-world entity segmentation, as an emerging computer vision task, aims at segmenting entities in images without being restricted by pre-defined classes, offering impressive gene…
Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores
Chantal Shaib, Venkata S. Govindarajan, Joe Barrow +4
The diversity across outputs generated by LLMs shapes perception of their quality and utility. High lexical diversity is often desirable, but there is no standard method to measure…
How Much Annotation is Needed to Compare Summarization Models?
Chantal Shaib, Joe Barrow, Alexa F. Siu +2
Modern instruction-tuned models have become highly capable in text generation tasks such as summarization, and are expected to be released at a steady pace. In practice one may now…
Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
Zhendong Chu, Ruiyi Zhang, Tong Yu +4
To achieve state-of-the-art performance, one still needs to train NER models on large-scale, high-quality annotated data, an asset that is both costly and time-intensive to accumul…
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Sicheng Zhu, Ruiyi Zhang, Bang An +6
Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against…
PDFTriage: Question Answering over Long, Structured Documents
Jon Saad-Falcon, Joe Barrow, Alexa Siu +4
Large Language Models (LLMs) have issues with document question answering (QA) in situations where the document is unable to fit in the small context length of an LLM. To overcome…
Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness
David Demeter, Oshin Agarwal, Simon Ben Igeri +4
Academic literature does not give much guidance on how to build the best possible customer-facing summarization system from existing research components. Here we present analyses t…
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning
Kaige Xie, Tong Yu, Haoliang Wang +6
In real-world scenarios, labeled samples for dialogue summarization are usually limited (i.e., few-shot) due to high annotation costs for high-quality dialogue summaries. To effici…
Learning the Visualness of Text Using Large Vision-Language Models
Gaurav Verma, Ryan A. Rossi, Christopher Tensmeyer +2
Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and ge…
Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Chieh-Yang Huang, Ting-Yao Hsu, Ryan Rossi +6
Good figure captions help paper readers understand complex scientific figures. Unfortunately, even published papers often have poorly written captions. Automatic caption generation…
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Zilong Wang, Jiuxiang Gu, Chris Tensmeyer +5
Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g…
Influence Functions for Sequence Tagging Models
Sarthak Jain, Varun Manjunatha, Byron C. Wallace +1
Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been…
Self-Repetition in Abstractive Neural Summarizers
Nikita Salkar, Thomas Trikalinos, Byron C. Wallace +1
We provide a quantitative and qualitative analysis of self-repetition in the output of neural summarizers. We measure self-repetition as the number of n-grams of length four or lon…
Unified Pretraining Framework for Document Understanding
Jiuxiang Gu, Jason Kuen, Vlad I. Morariu +5
Document intelligence automates the extraction of information from documents and supports many business applications. Recent self-supervised learning methods on large-scale unlabel…
Temporal Effects on Pre-trained Models for Language Processing Tasks
Oshin Agarwal, Ani Nenkova
Keeping the performance of language technologies optimal as time passes is of great practical interest. We study temporal effects on model performance on downstream language tasks,…
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
Anushree Hede, Oshin Agarwal, Linda Lu +2
The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists. Computational tools for detecting online incivility f…
Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations
Benjamin E. Nye, Jay DeYoung, Eric Lehman +3
The best evidence concerning comparative treatment effectiveness comes from clinical trials, the results of which are reported in unstructured articles. Medical experts must manual…
Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time
Benjamin E. Nye, Ani Nenkova, Iain J. Marshall +1
We introduce Trialstreamer, a living database of clinical trial reports. Here we mainly describe the evidence extraction component; this extracts from biomedical abstracts key piec…
Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve
Oshin Agarwal, Yinfei Yang, Byron C. Wallace +1
Named Entity Recognition systems achieve remarkable performance on domains such as English news. It is natural to ask: What are these models actually learning to achieve this? Are…
Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models
Oshin Agarwal, Yinfei Yang, Byron C. Wallace +1
Named entity recognition systems perform well on standard datasets comprising English news. But given the paucity of data, it is difficult to draw conclusions about the robustness…