57 citations · 69 across the 12 of their papers we have counts for
12 papers
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
Sophia Xiao Pu, Yumo Xu, Sailik Sengupta +5
Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retaining it whole or discarding it…
MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline
Fang-Duo Tsai, Yi-An Lai, Fei-Yueh Chen +4
While end-to-end lyrics-to-song models offer convenience for casual users, professional songwriters require score-to-song systems that allow them to retain authorship over the core…
DeAL: Decoding-time Alignment for Large Language Models
James Y. Huang, Sailik Sengupta, Daniele Bonadiman +6
Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. Current work focuses on alignment at model training time, through techniques…
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
Yi-An Lai, Elman Mansimov, Yuqing Xie +1
When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavio…
Backward Compatibility During Data Updates by Weight Interpolation
Raphael Schumann, Elman Mansimov, Yi-An Lai +3
Backward compatibility of model predictions is a desired property when updating a machine learning driven application. It allows to seamlessly improve the underlying model without…
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
Deng Cai, Elman Mansimov, Yi-An Lai +3
Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backwar…
Efficient Domain Adaptation of Language Models via Adaptive Tokenization
Vin Sachidananda, Jason S. Kessler, Yi-an Lai
Contextual embedding-based language models trained on large data sets, such as BERT and RoBERTa, provide strong performance across a wide range of tasks and are ubiquitous in moder…
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Yixuan Su, Lei Shu, Elman Mansimov +4
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascade…
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Yuqing Xie, Yi-an Lai, Yuanjun Xiong +2
Behavior of deep neural networks can be inconsistent between different versions. Regressions during model update are a common cause of concern that often over-weigh the benefits in…
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
Yi-An Lai, Xuan Zhu, Yi Zhang +1
Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point. However, as natural language processing methods flourish, t…
Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation
Yi-An Lai, Arshit Gupta, Yi Zhang
Hierarchical neural networks are often used to model inherent structures within dialogues. For goal-oriented dialogues, these models miss a mechanism adhering to the goals and negl…
Attribute-aware Collaborative Filtering: Survey and Classification
Wen-Hao Chen, Chin-Chi Hsu, Yi-An Lai +3
Attribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e.g. age), items (e.g.…