134 citations · 718 across the 111 of their papers we have counts for
114 papers
RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment
Kevin Yang, Dan Klein, Asli Celikyilmaz +2
We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more h…
DesCo: Learning Object Recognition with Rich Language Descriptions
Liunian Harold Li, Zi-Yi Dou, Nanyun Peng +1
Recent development in vision-language approaches has instigated a paradigm shift in learning visual recognition models from language supervision. These approaches align objects wit…
Next Steps for Human-Centered Generative AI: A Technical Perspective
Xiang 'Anthony' Chen, Jeff Burke, Ruofei Du +8
Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI). We contribute a comprehensive research agenda that lays…
Open-Domain Text Evaluation via Contrastive Distribution Methods
Sidi Lu, Hongyi Liu, Asli Celikyilmaz +2
Recent advancements in open-domain text generation, driven by the power of large pre-trained language models (LLMs), have demonstrated remarkable performance. However, assessing th…
DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
Sidi Lu, Wenbo Zhao, Chenyang Tao +4
NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving gua…
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model
I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang +2
Event argument extraction (EAE) identifies event arguments and their specific roles for a given event. Recent advancement in generation-based EAE models has shown great performance…
Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children's Fairy Tales
Paulina Toro Isaza, Guangxuan Xu, Akintoye Oloko +3
Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literatur…
Unsupervised Melody-Guided Lyrics Generation
Yufei Tian, Anjali Narayan-Chen, Shereen Oraby +7
Automatic song writing is a topic of significant practical interest. However, its research is largely hindered by the lack of training data due to copyright concerns and challenged…
Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning
Po-Nien Kung, Nanyun Peng
Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) p…
Identifying Informational Sources in News Articles
Alexander Spangher, Nanyun Peng, Jonathan May +1
News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand th…
Masked Path Modeling for Vision-and-Language Navigation
Zi-Yi Dou, Feng Gao, Nanyun Peng
Vision-and-language navigation (VLN) agents are trained to navigate in real-world environments by following natural language instructions. A major challenge in VLN is the limited a…
Unsupervised Melody-to-Lyric Generation
Yufei Tian, Anjali Narayan-Chen, Shereen Oraby +8
Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody. It is of significant practical interest and more challenging than uncon…
Code-Switched Text Synthesis in Unseen Language Pairs
I-Hung Hsu, Avik Ray, Shubham Garg +2
Existing efforts on text synthesis for code-switching mostly require training on code-switched texts in the target language pairs, limiting the deployment of the models to cases la…
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung +3
Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific traini…
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
Sarik Ghazarian, Yijia Shao, Rujun Han +2
Commonsense reasoning is omnipresent in human communications and thus is an important feature for open-domain dialogue systems. However, evaluating commonsense in dialogue systems…
Tractable Control for Autoregressive Language Generation
Honghua Zhang, Meihua Dang, Nanyun Peng +1
Despite the success of autoregressive large language models in text generation, it remains a major challenge to generate text that satisfies complex constraints: sampling from the…
Sequentially Controlled Text Generation
Alexander Spangher, Xinyu Hua, Yao Ming +1
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structu…
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
Mingyu Derek Ma, Jiun-Yu Kao, Shuyang Gao +4
Dialogue state tracking (DST) is an important step in dialogue management to keep track of users' beliefs. Existing works fine-tune all language model (LM) parameters to tackle the…
Generalized Decoding for Pixel, Image, and Language
Xueyan Zou, Zi-Yi Dou, Jianwei Yang +11
We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decodert takes as input two types of queries: (i) gen…
Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts
Arshiya Aggarwal, Jiao Sun, Nanyun Peng
We present a robust methodology for evaluating biases in natural language generation(NLG) systems. Previous works use fixed hand-crafted prefix templates with mentions of various d…
DOC: Improving Long Story Coherence With Detailed Outline Control
Kevin Yang, Dan Klein, Nanyun Peng +1
We propose the Detailed Outline Control (DOC) framework for improving long-range plot coherence when automatically generating several-thousand-word-long stories. DOC consists of tw…
A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scale
Zhixuan Zhou, Jiao Sun, Jiaxin Pei +2
Fairy tales are a common resource for young children to learn a language or understand how a society works. However, gender bias, e.g., stereotypical gender roles, in this literatu…
Context-Situated Pun Generation
Jiao Sun, Anjali Narayan-Chen, Shereen Oraby +5
Previous work on pun generation commonly begins with a given pun word (a pair of homophones for heterographic pun generation and a polyseme for homographic pun generation) and seek…
ExPUNations: Augmenting Puns with Keywords and Explanations
Jiao Sun, Anjali Narayan-Chen, Shereen Oraby +5
The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master. Puns, in particular, add t…