Search Results for author: Yijia Shao

Found 19 papers, 13 papers with code

Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce

no code implementations6 Jun 2025 Yijia Shao, Humishka Zope, Yucheng Jiang, Jiaxin Pei, David Nguyen, Erik Brynjolfsson, Diyi Yang

The rapid rise of compound AI systems (a. k. a., AI agents) is reshaping the labor market, raising concerns about job displacement, diminished human agency, and overreliance on automation.

AI Agent

Challenges and Paths Towards AI for Software Engineering

no code implementations28 Mar 2025 Alex Gu, Naman jain, Wen-Ding Li, Manish Shetty, Yijia Shao, Ziyang Li, Diyi Yang, Kevin Ellis, Koushik Sen, Armando Solar-Lezama

First, we provide a structured taxonomy of concrete tasks in AI for software engineering, emphasizing the many other tasks in software engineering beyond code generation and completion.

Code Generation

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

1 code implementation29 Aug 2024 Yijia Shao, Tianshi Li, Weiyan Shi, Yanchen Liu, Diyi Yang

However, quantifying the privacy norm awareness of LMs and the emerging privacy risk in LM-mediated communication is challenging due to (1) the contextual and long-tailed nature of privacy-sensitive cases, and (2) the lack of evaluation approaches that capture realistic application scenarios.

Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations

1 code implementation27 Aug 2024 Yucheng Jiang, Yijia Shao, Dekun Ma, Sina J. Semnani, Monica S. Lam

While language model (LM)-powered chatbots and generative search engines excel at answering concrete queries, discovering information in the terrain of unknown unknowns remains challenging for users.

Sentiment Analysis

Aligning Language Models with Demonstrated Feedback

1 code implementation2 Jun 2024 Omar Shaikh, Michelle S. Lam, Joey Hejna, Yijia Shao, Hyundong Cho, Michael S. Bernstein, Diyi Yang

We argue that it is instead possible to align an LLM to a specific setting by leveraging a very small number (< 10) of demonstrations as feedback.

Articles Avg +3

Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models

2 code implementations22 Feb 2024 Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, Monica S. Lam

We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages.

Articles Retrieval

Class Incremental Learning via Likelihood Ratio Based Task Prediction

2 code implementations26 Sep 2023 Haowei Lin, Yijia Shao, Weinan Qian, Ningxin Pan, Yiduo Guo, Bing Liu

An emerging theory-guided approach (called TIL+OOD) is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with catastrophic forgetting.

class-incremental learning Class Incremental Learning +2

Class-Incremental Learning based on Label Generation

1 code implementation22 Jun 2023 Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu

Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF).

class-incremental learning Class Incremental Learning +1

ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems

1 code implementation12 May 2023 Sarik Ghazarian, Yijia Shao, Rujun Han, Aram Galstyan, Nanyun Peng

We take the first step by focusing on event commonsense that considers events and their relations, and is crucial in both dialogues and general commonsense reasoning.

Adapting a Language Model While Preserving its General Knowledge

2 code implementations21 Jan 2023 Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu

This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge.

Continual Learning General Knowledge +2

LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training

1 code implementation6 Dec 2022 Hongwei Han, Jialiang Xu, Mengyu Zhou, Yijia Shao, Shi Han, Dongmei Zhang

But current approaches to rich-number tasks with transformer-based language models abandon or lose some of the numeracy information - e. g., breaking numbers into sub-word tokens - which leads to many number-related errors.

FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information

no code implementations10 Nov 2022 Yijia Shao, Mengyu Zhou, Yifan Zhong, Tao Wu, Hongwei Han, Shi Han, Gideon Huang, Dongmei Zhang

To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion).

Form Language Modeling +1

Continual Training of Language Models for Few-Shot Learning

3 code implementations11 Oct 2022 Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, Bing Liu

Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.

Continual Learning Continual Pretraining +2

Efficient Out-of-Distribution Detection via CVAE data Generation

no code implementations29 Sep 2021 Mengyu Wang, Yijia Shao, Haowei Lin, Wenpeng Hu, Bing Liu

Recently, contrastive loss with data augmentation and pseudo class creation has been shown to produce markedly better results for out-of-distribution (OOD) detection than previous methods.

Data Augmentation Out-of-Distribution Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.