Papers by Sheng Jin

5 papers
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)

Copied to clipboard

Challenge: Existing surveys on scientific LLMs focus on one or two fields or a single modality.
Approach: They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures .
Outcome: The proposed model architectures and evaluation techniques are used to improve scientific discovery.
EMNLP: Educator-role Moral and Normative Large Language Models Profiling (2025.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks for evaluating the ethical and moral alignment of large language models (LLMs) in educational AI are lacking.
Approach: They propose a framework for a teacher-role moral and normative LLMs profiling . they extend existing scales and construct 88 teacher-specific moral dilemmas .
Outcome: The proposed framework evaluates compliance and vulnerability of teacher-role LLMs under soft prompt injection.
Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection (2023.acl-industry)

Copied to clipboard

Challenge: Existing work on fake news detection does not consider the temporal shift issue caused by the rapidly-evolving nature of news data.
Approach: They propose a framework to forecast temporal patterns of news data and guide detector to fast adapt to future distributions.
Outcome: The proposed framework forecasts temporal distribution patterns and guides detector to fast adapt to future distribution.
Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) based Agents are increasingly pivotal in simulating complex human systems and interactions.
Approach: They propose an AI-Agent School system that leverages agents for simulating educational dynamics.
Outcome: The proposed system can simulate complex educational dynamics in simulated schools.
Locally Aggregated Feature Attribution on Natural Language Model Understanding (2022.naacl-main)

Copied to clipboard

Challenge: a growing popularity of deep-learning models makes model understanding more important . feature attribution methods have shown promising results in computer vision but are not trivial .
Approach: They propose a gradient-based feature attribution method that smooths gradients by aggregating similar reference texts derived from language model embeddings.
Outcome: The proposed method outperforms existing methods on public datasets and key words detection tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations