24 citations · 51 across the 15 of their papers we have counts for
15 papers
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Wenda Xu, Rujun Han, Zifeng Wang +7
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised…
Uncovering Factor Level Preferences to Improve Human-Model Alignment
Juhyun Oh, Eunsu Kim, Jiseon Kim +4
Large language models (LLMs) often exhibit tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. While crucia…
BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
Wenda Xu, Jiachen Li, William Yang Wang +1
Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference dat…
Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
Wenda Xu, Guanglei Zhu, Xuandong Zhao +3
Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary i…
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
Wenda Xu, Daniel Deutsch, Mara Finkelstein +6
Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In t…
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Liangming Pan, Michael Saxon, Wenda Xu +3
Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behavior…
INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback
Wenda Xu, Danqing Wang, Liangming Pan +4
Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain t…
CausalDialogue: Modeling Utterance-level Causality in Conversations
Yi-Lin Tuan, Alon Albalak, Wenda Xu +4
Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and…
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
Wenda Xu, Xian Qian, Mingxuan Wang +2
Is it possible to train a general metric for evaluating text generation quality without human annotated ratings? Existing learned metrics either perform unsatisfactorily across tex…
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Wenda Xu, Yilin Tuan, Yujie Lu +3
Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to t…
Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Wanrong Zhu, An Yan, Yujie Lu +4
Recent advances in text-to-image synthesis make it possible to visualize machine imaginations for a given context. On the other hand, when generating text, human writers are gifted…
Neuro-Symbolic Procedural Planning with Commonsense Prompting
Yujie Lu, Weixi Feng, Wanrong Zhu +4
Procedural planning aims to implement complex high-level goals by decomposition into sequential simpler low-level steps. Although procedural planning is a basic skill set for human…
PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers
Michael Saxon, Xinyi Wang, Wenda Xu +1
Building natural language inference (NLI) benchmarks that are both challenging for modern techniques, and free from shortcut biases is difficult. Chief among these biases is "singl…
Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer
Wenda Xu, Michael Saxon, Misha Sra +1
Expert-layman text style transfer technologies have the potential to improve communication between members of scientific communities and the general public. High-quality informatio…
Fake News Detection with Different Models
Sairamvinay Vijayaraghavan, Ye Wang, Zhiyuan Guo +7
This is a paper for exploring various different models aiming at developing fake news detection models and we had used certain machine learning algorithms and we had used pretraine…