Guanting Dong

Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement

2023 · arXiv (Cornell University)

Emotion Recognition in Conversation (ERC) has attracted widespread attention in the natural language processing field due to its enormous potential for practical applications. Existing ERC methods face challenges in achieving generalization to diverse scenarios due …

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

2024 · arXiv (Cornell University)

Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect …

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

2024

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long …

Progressive Multimodal Reasoning via Active Retrieval

2024 · arXiv (Cornell University)

Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose AR-MCTS, a …

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

2025

Retrieval-augmented generation (RAG) has effectively mitigated the hallucination problem of large language models (LLMs). However, the difficulty of aligning the retriever with the LLMs' diverse knowledge preferences inevitably poses a challenge in developing a reliable …