Search Results for author:
Found 22 papers, 12 papers with code
AESOP: Paraphrase Generation with Adaptive Syntactic Control
We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases.
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations
While these tasks partially evaluate machines’ ability of narrative understanding, human-like reading comprehension requires the capability to process event-based information beyond arguments and temporal reasoning.
Rich Human Feedback for Text-to-Image Generation
We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions.
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
Then, it uses two VLMs to select the best generation: a Visual Question Answering model that measures the alignment of generated images to the text, and another that measures the generation's aesthetic quality.
Evaluating Large Language Models on Controlled Generation Tasks
While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc, there have been few studies looking into the controllability of large language models on generation tasks.
"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters
Through benchmarking evaluation on 2 popular LLMs- ChatGPT and Alpaca, we reveal significant gender biases in LLM-generated recommendation letters.
LIMA: Less Is More for Alignment
Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences.
Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts
These fixed prefix templates could themselves be specific in terms of styles or linguistic structures, which may lead to unreliable fairness conclusions that are not representative of the general trends from tone varying prompts.
A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scale
Our analysis further reveal stereotypical portrayals of both male and female characters in terms of moral foundations and events.
Dialect-robust Evaluation of Generated Text
Evaluation metrics that are not robust to dialect variation make it impossible to tell how well systems perform for many groups of users, and can even penalize systems for producing text in lower-resource dialects.
Context-Situated Pun Generation
In this work, we propose a new task, context-situated pun generation, where a specific context represented by a set of keywords is provided, and the task is to first identify suitable pun words that are appropriate for the context, then generate puns based on the context keywords and the identified pun words.
ExPUNations: Augmenting Puns with Keywords and Explanations
The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master.
Investigating the Benefits of Free-Form Rationales
After controlling for instances where rationales leak the correct answer while not providing additional background knowledge, we find that incorporating only 5% of rationales during training can boost model performance by 47. 22% for CoS-E and 57. 14% for ECQA during inference.
Helpfulness and Fairness of Task-Oriented Dialogue Systems
Then, we collect human annotations for the helpfulness of dialogue responses based on our definition and build a classifier to automatically determine the helpfulness of a response.
Investigating Explainability of Generative AI for Code through Scenario-based Design
Using scenario-based design and question-driven XAI design approaches, we explore users' explainability needs for GenAI in three software engineering use cases: natural language to code, code translation, and code auto-completion.
HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting
Based on the homophily assumption of GNN, we propose a homophily-aware constraint to regularize the optimization of the region graph so that neighboring region nodes on the learned graph share similar crime patterns, thus fitting the mechanism of diffusion convolution.
On Measures of Biases and Harms in NLP
Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality.
Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia
Human activities can be seen as sequences of events, which are crucial to understanding societies.
ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning
While these tasks partially evaluate machines' ability of narrative understanding, human-like reading comprehension requires the capability to process event-based information beyond arguments and temporal reasoning.
EventPlus: A Temporal Event Understanding Pipeline
We present EventPlus, a temporal event understanding pipeline that integrates various state-of-the-art event understanding components including event trigger and type detection, event argument detection, event duration and temporal relation extraction.
FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems
In both letter-level and word-level attacks, our experiments show that in addition to natural appearance, FAWA achieves a 100% attack success rate with 60% less perturbations and 78% fewer iterations on average.
Optical Character Recognition
Optical Character Recognition (OCR)
Catching Loosely Synchronized Behavior in Face of Camouflage
Fraud has severely detrimental impacts on the business of social networks and other online applications.
Social and Information Networks Cryptography and Security
