Papers by Ziqi Jin

4 papers
Self-Harmonized Chain of Thought (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for chain-of-thought prompting have limitations . arithmetic, commonsense, and symbolic reasoning tasks are challenging .
Approach: They propose a method that unifies diverse solution paths into a consistent reasoning pattern.
Outcome: The proposed method outperforms existing methods by 2.8% on reasoning tasks.
Sailor: Open Language Models for South-East Asia (2024.emnlp-demo)

Copied to clipboard

Challenge: Large language models (LLMs) rely on English data for training, but are often not comparable across other languages.
Approach: They propose to develop a family of open language models for SEA languages . they use BPE dropout, aggressive data cleaning and deduplication to improve model robustness .
Outcome: The proposed models perform well across four benchmarks, including commonsense reasoning, question answering, reading comprehension and examination.
Tab-CoT: Zero-shot Tabular Chain of Thought (2023.findings-acl)

Copied to clipboard

Challenge: Recent efforts to encourage more structured reasoning procedures to be captured have shown that chain-of-though (CoT) prompting methods can be effective in NLP tasks.
Approach: They propose a tabular-format CoT prompting method that allows the complex reasoning process to be explicitly modeled in a highly structured manner.
Outcome: The proposed method shows impressive performance improvements on a range of reasoning 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