Papers by Zihan Qin

7 papers
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges (2026.findings-acl)

Copied to clipboard

Challenge: Increasing saturation of web data limits further scaling of model intelligence.
Approach: They propose a benchmark to evaluate machine creativity in code generation that combines combinatorial and exploratory creativity through reverse engineering and self-play.
Outcome: The proposed benchmark targets combinatorial and exploratory creativity through reverse engineering and self-play.
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: Comparative Preference Classification (CPC) is a natural language processing task that predicts whether a preference comparison exists between two entities in a given sentence .
Approach: They propose a sentiment analyzer that learns sentiments to individual entities via domain adaptive knowledge transfer.
Outcome: Experiments on the CompSent-19 dataset present a significant improvement on the F1 scores over the best existing CPC approaches.
Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)

Copied to clipboard

Challenge: Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student.
Approach: They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions.
Outcome: The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures.
WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach: They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome: The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .
A Semantic Search Engine for Mathlib4 (2024.findings-emnlp)

Copied to clipboard

Challenge: Lean is an interactive theorem prover that enables verification of formal proofs . however, searching for theoretical proofs in mathlib4 can be challenging for beginners . we present a semantic search engine that accepts informal queries and finds theorels .
Approach: They propose a semantic search engine for theorems in mathlib4 that accepts informal queries and finds relevant theorels.
Outcome: The proposed search engine accepts informal queries and finds theorems . it compares with other search engines that struggle to find theoretical proofs based on informal queries .
MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)

Copied to clipboard

Challenge: Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations.
Approach: They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency.
Outcome: The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types.
Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Existing research on multi-modal Named Entity Recognition (MNER) does not integrate all multi-modal representations to provide rich contextual information to improve NER.
Approach: They propose an iterative reasoning framework that integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate" . they propose to use hierarchically connected fusion layers to prioritize transitions from "easy-to-hard" and "coarse-to fine"
Outcome: The proposed framework integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate".

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