Papers by Hongzhi Liu

7 papers
Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks and evaluation protocols suffer from inadequate or homogeneous creation of key points, exorbitant cost of data creation, and limited evaluation scopes.
Approach: They propose an automatic framework which leverages Monte Carlo Tree Search to construct numerous and diverse descriptive sentences that thoroughly represent video content in an iterative way.
Outcome: The proposed framework improves MCTS-VCB and DREAM-1K on video captioning tasks by 25.0% and 16.3% respectively.
Data-Anonymous Encoding for Text-to-SQL Generation (D19-1)

Copied to clipboard

Challenge: Existing approaches to handle table-related tokens before the semantic parser are not efficient . existing approaches ignore handling table- related tokens or use deterministic approaches based on string-match or word embedding similarity.
Approach: They propose a more efficient approach to handle table-related tokens before the parser . they propose tagging a sequential tabbing problem and an implicit supervision approach .
Outcome: The proposed approach significantly outperforms deterministic approaches.
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems (2022.findings-acl)

Copied to clipboard

Challenge: Existing models memorize procedures from context and rely on shallow heuristics to solve MWPs.
Approach: They propose a contrastive learning approach where the neural network perceives the divergence of patterns.
Outcome: The proposed method greatly improves performance in monolingual and multilingual settings.
Representation Learning with Ordered Relation Paths for Knowledge Graph Completion (D19-1)

Copied to clipboard

Challenge: Existing knowledge graphs are incomplete and lack the order of relations in paths.
Approach: They propose a method which takes relation paths into account but ignores order of relations in paths which is important for reasoning.
Outcome: The proposed method performs better than state-of-the-art methods on two benchmark datasets.
Are Large Language Models (LLMs) Good Social Predictors? (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies suggest that Large Language Models can generate human-like responses, but it is unclear how well they work and where the plausible predictions derive from.
Approach: They propose to use LLMs to generate human-like responses by mutability and accessibility of social inputs to perform a social prediction task.
Outcome: The proposed model performs well in three realistic settings and a novel social prediction task.
Annotating Chinese Word Senses with English WordNet: A Practice on OntoNotes Chinese Sense Inventories (2024.lrec-main)

Copied to clipboard

Challenge: a recent study has shown that large language models can be useful for cross-lingual applications.
Approach: They propose to annotate Chinese word senses using English WordNet synsets . they examine the relationship between two annotators and find patterns among synset .
Outcome: The proposed method shows that the annotators agree on 38% of the synsets compared with the original synset . the results highlight similarities between the synnotated synset and the WordNet structure .
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to correct handwritten assignments are to use OCR to recognize characters and compare them to answers.
Approach: They propose a multimodal approach to correct handwritten Chinese characters by combining the visual information of students' handwriting with the encoded representations of answers.
Outcome: The proposed model outperforms OCR-based methods by a large margin.

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