Papers by Zhiqing Sun

9 papers
Improve Vision Language Model Chain-of-thought Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Current training recipes often rely on datasets dominated by short annotations with limited rationales, hindering the models' ability to generalize to tasks requiring comprehensive reasoning.
Approach: They propose a two-stage post-training strategy that augments short answers with CoT reasoning generated by GPT-4o, enhancing the VLM's CoT capabilities through fine-tuning.
Outcome: The proposed strategy enhances the model's CoT capabilities through fine-tuning and reinforcement learning.
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts (2022.acl-demo)

Copied to clipboard

Challenge: PromptSource is a system for creating, sharing, and using natural language prompts . prompts are used to train and query language models in zero-shot learning settings .
Approach: PromptSource is a system for creating, sharing, and using natural language prompts . et al.: using prompts to train and query language models is emerging area in NLP . they propose a templating language for defining data-linked prompts, a user interface that iterates on prompt development .
Outcome: PromptSource is a system for creating, sharing, and using natural language prompts . it has a templating language for defining data-linked prompts and a community-driven set of guidelines .
A Re-evaluation of Knowledge Graph Completion Methods (2020.acl-main)

Copied to clipboard

Challenge: Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs.
Approach: They propose a protocol to evaluate KGC methods that is robust to handle bias in the model, which can substantially affect the final results.
Outcome: The proposed evaluation protocol is robust to handle bias in the model, which can substantially affect the final results.
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices (2020.acl-main)

Copied to clipboard

Challenge: Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE . BERT is one of the largest models ever in NLP, but suffers from heavy model size and high latency .
Approach: They propose a tool to compress and accelerate the popular BERT model by task-agnostic application.
Outcome: The proposed model is 4.3x smaller and 5.5x faster than BERT_BASE . it achieves competitive results on well-known benchmarks .
Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have demonstrated that direct preference optimization (DPO) can be effective in generalizing large language models, but its effectiveness in video domain remains limited.
Approach: They propose a framework that utilizes detailed video captions as a proxy of video content to enable language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions.
Outcome: The proposed framework shows that it can be used to align language models with video content and improves performance on open-ended video QA tasks.
Instruction-tuned Language Models are Better Knowledge Learners (2024.acl-long)

Copied to clipboard

Challenge: Large language models store factual knowledge in parameters, but it can become outdated as the work evolves . pre-instruction-tuning improves ability of LLMs to absorb knowledge from new documents .
Approach: They propose a method that instruction-tunes on questions prior to training on documents . they propose to use QA pairs to update factual knowledge of large language models .
Outcome: The proposed method outperforms instruction-tuning on documents by 17.8%.
Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach: They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome: The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.
Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling (D18-1)

Copied to clipboard

Challenge: Existing approaches to unsupervised Chinese word segmentation (CWS) are discriminative and generative, but they are non-trivial.
Approach: They propose a neural generative model for fully unsupervised Chinese word segmentation (CWS) their approach explicitly focuses on the segmental nature of Chinese, and preserves several properties of language models.
Outcome: The proposed model achieves competitive performance to the state-of-the-art models on four datasets from SIGHAN 2005 bakeoff.
Active Retrieval Augmented Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Generative language models (LMs) have a tendency to hallucinate and create inaccurate output.
Approach: They propose a method which iteratively uses a prediction of the upcoming sentence to anticipate future content.
Outcome: The proposed method achieves superior or competitive performance on all tasks . iteratively uses a prediction of the upcoming sentence to anticipate future content .

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