add EMNLP 2023 paper

_pages/cv.md

@@ -12,7 +12,7 @@ redirect_from:
 {% include base_path %}
 
 Yixuan Cao is an Associate Professor in Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS).
-His research interest includes NLP, Document Intelligence, and Structured Information Extraction. He is working on an exciting project that brings AI technology to finance.
+His research interest includes NLP, Document Intelligence, and Trustworthy AI (expecially hallucination in LLM). He is working on an exciting project that brings AI technology to finance.
 
 Always looking for self-motivated interns with a strong interest/background in NLP / machine learning / data mining. 
 
@@ -28,6 +28,6 @@ Education
 
 Publications
 ======
- <ul>{% for post in site.publications %}
+ <ul>{% for post in site.publications reversed %}
  {% include archive-single-cv.html %}
  {% endfor %}</ul>

_publications/2023-11-01-EMNLP.md

@@ -0,0 +1,21 @@
+---
+title: "Guideline Learning for In-Context Information Extraction"
+collection: publications
+permalink: /publication/2023-11-01-EMNLP
+excerpt: 'We propose to learn the task description (guideline) to learn from training samples for in-context learning'
+date: 2023-11-01
+venue: 'EMNLP'
+paperurl: 'https://aclanthology.org/2023.emnlp-main.950/'
+citation: 'Chaoxu Pang, Yixuan Cao, Qiang Ding, and Ping Luo. 2023. Guideline Learning for In-Context Information Extraction. In EMNLP, 2023.'
+---
+
+Machine learning algorithms typically learn by updating parameters. But in the era of large models, updating parameters becomes infeasible for many closed-source models. Therefore, how can learning be achieved without updating model parameters, thereby enhancing the model's in-context learning capabilities?
+
+We have proposed a **Guideline Learning** framework based on in-context learning. A guideline refers to text used to describe tasks, similar to the instructions given to annotators during the labeling process. This framework can generate and follow guidelines, enabling the model to learn a series of task guidelines from error samples without updating its parameters. Experiments in event extraction and relation extraction have shown that Guideline Learning improves the performance of in-context learning in information extraction tasks. This suggests that learning task instructions without updating parameters can serve as a new approach to learning.
+
+
+[The Guideline Learning Framework.](/images/guideline-learning.png)
+On the leftside of the figure, during inference, given an input query, the framework retrieve relevant guideline rules to conduct in-context learning. On the rightside, during training, given an input query, the prediction and the annotation are feed into the LLM to refect and generate (update) relavant guideline rules. The training output is a set of guideline rules.
+
+
+[paper](https://aclanthology.org/2023.emnlp-main.950/)