Papers by Haolong Li

5 papers
Exploring Mathematical Extrapolation of Large Language Models with Synthetic Data (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have shown excellent capabilities in language understanding, text generation and many other tasks, but struggle in complex multi-step reasoning problems such as mathematical reasoning.
Approach: They propose to fine tune an open-llama-3B model to perform well on multi-step reasoning tasks via synthetic data.
Outcome: The proposed model can reach a zero-shot pass@1 at 0.44 on the in-domain dataset and demonstrates certain generalization capabilities on the out-of-domain data.
Leveraging Generative Large Language Models with Visual Instruction and Demonstration Retrieval for Multimodal Sarcasm Detection (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for multimodal sarcasm detection do not fully utilize cross-modal features, limiting their performance on in-domain datasets.
Approach: They propose a multimodal sarcasm detection model with a designed instruction template and a demonstration retrieval module.
Outcome: The proposed model outperforms existing methods on in-domain datasets and achieves state-of-the-art performance.
Visual Enhanced Entity-Level Interaction Network for Multimodal Summarization (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to generate concise summarizations rely on coarse-grained textual and visual information, but they are underutilized.
Approach: They propose a Visual Enhanced Entity-Level Interaction Network to address underutilization of multimodal inputs at a fine-grained level.
Outcome: The proposed model outperforms existing models on two MMS datasets and proposes new metrics to measure factual consistency of entities in the output.
Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for name-based entity recognition neglect the integrity of entity semantics and conduct cross-modal interaction at token-level.
Approach: They propose a multimodal named entity recognition model that captures visual information and fuses it into tokens to rid non-entity tokens of visual noise.
Outcome: The proposed model captures entity-related visual information and fuses it into tokens . it eliminates visual noise and makes non-entity tokens easily misidentified as entities .
Complete Chess Games Enable LLM Become A Chess Master (2025.naacl-short)

Copied to clipboard

Challenge: Large language models (LLMs) have shown remarkable abilities in text generation, question answering, language translation, reasoning and many other tasks.
Approach: They propose a Large language model that can play chess games by transforming a game into a textual format with the best move represented in the Forsyth-Edwards Notation.
Outcome: The proposed model achieves professional-level Elo rating of 1788 in matches against the standard Elo-rated Stockfish when permitted to sample 10 times.

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