Papers by Jinhua Cheng

6 papers
ALiiCE: Evaluating Positional Fine-grained Citation Generation (2025.naacl-long)

Copied to clipboard

Challenge: Existing research on citation generation is limited to sentence-level statements . positional fine-grained citations can appear anywhere within sentences .
Approach: They propose a framework that allows LLMs to generate citations from sentences . they use dependency tree-based methods to parse sentence-level claims into atomic claims .
Outcome: The proposed framework evaluates citation quality using three metrics including positional fine-grained citation recall, precision, and coefficient of variation of citation positions.
A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages.
Approach: They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies.
Outcome: The proposed model can be used to understand and generate human natural languages.
Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Utility-based retrieval has emerged as a promising topic for downstream tasks . however, capturing passage utility accurately remains unexplored due to insufficient understanding .
Approach: They propose a framework for training utility-based retrievers in Retrieval-Augmented Language Models . it incorporates multi-task generalization and inter-passage interaction to improve performance .
Outcome: The proposed framework improves performance on ten datasets across different tasks.
Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach: They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome: The proposed method outperforms baseline methods on small and large scale machine translation datasets.
TKGT: Redefinition and A New Way of Text-to-Table Tasks Based on Real World Demands and Knowledge Graphs Augmented LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on text-to-table tasks that ignore domain structures and use simple datasets to extract structured information from unstructured text.
Approach: They propose a new text-to-table task that generates domain knowledge graphs from raw text using a mixed-IE method and a hybrid retrieval augmented generation method.
Outcome: The proposed dataset improves compatibility with long text-processing tasks by incorporating domain knowledge graphs (KGs) classes into tables.
TST: A Schema-Based Top-Down and Dynamic-Aware Agent of Text-to-Table Tasks (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to extract text content based on static table structures neglect to deal with precise inner-document evidence extraction and dynamic information such as multiple entities and events.
Approach: They propose a dynamic content extraction agent framework that uses type recognition to extract context evidences with the conduction of domain schema sequentially.
Outcome: The proposed framework exhibits state-of-the-art (SOTA) performance on a large dataset.

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