Papers by Zhang Yunfei

13 papers
Span-level Aspect-based Sentiment Analysis via Table Filling (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to analyze aspect-based sentiment analysis focus on word-level dependencies between aspect and opinion expressions.
Approach: They propose a span-level ABSA model which considers consistency of multi-word opinion expressions at the span- level.
Outcome: The proposed model can be used to identify the sentiment polarity of a given aspect . it is based on a table filling method and a regularizer to guarantee consistency .
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach: They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome: The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach: They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome: The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.
NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for evaluating novelty have been proposed, but there is no systematic evaluation of their ability to generate novelty evaluations.
Approach: They propose a benchmark to evaluate large language models’ ability to generate novelty evaluations in support of human peer review.
Outcome: The proposed framework evaluates the quality of LLM-generated novelty evaluations under different prompting strategies.
MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions (2025.coling-main)

Copied to clipboard

Challenge: Existing studies focus on summarization and question-answering tasks, but neglect logical coherence within stories.
Approach: They propose a model that leverages large language models to identify narrative gaps and generate coherent sentences that integrate seamlessly with the story’s emotional and logical flow.
Outcome: The proposed model enhances narrative understanding and story generation, highlighting LLMs’ potential as effective logic checkers in story writing with logical coherence and emotional consistency.
CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination.
Approach: They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns.
Outcome: The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages.
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)

Copied to clipboard

Challenge: Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge .
Approach: They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST .
Outcome: The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance .
Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to integrate thoughts with actions can cause irreversible error propagation . Xi et al., 2023; Zhang eet coll., 2023) have focused on enhancing large language model (LLM) agents capable of helping humans tackle real-world challenges.
Approach: They propose a framework called Generator-Assistant Stepwise Rollback to induce better decision-making for LLM agents by integrating a generator and an assistant to examine each action produced by the generator.
Outcome: The proposed framework improves on three widely used benchmarks and can integrate seamlessly with other methods.
Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches prioritize task-specific performance metrics over human-like comprehension of narrative context and gameplay logic.
Approach: They propose a framework that guides Large Language Models to learn and play IF games systematically.
Outcome: The proposed framework aligns LLMs-based agents’ behavior with narrative intent and commonsense constraints to deliver more interpretable, human-like performance.
Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs).
Approach: They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals.
Outcome: Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B.
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis (2022.coling-1)

Copied to clipboard

Challenge: Existing studies in Multimodal Sentiment Analysis lack a mechanism to understand complex relations between different modalities.
Approach: They propose a hierarchical graph contrastive learning framework for multimodal sentiment analysis that explores the relationships between modality representations.
Outcome: The proposed framework outperforms the state-of-the-art in multimodal sentiment analysis on two benchmark datasets.
MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms? (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, the top-performing models achieve a 48.8% task completion rate on realizing machine learning algorithms .
Approach: They propose a benchmark to test machine learning's ability to generate ML code for humans . they propose an automatic evaluation framework with metrics such as task pass rate and time overhead .
Outcome: The proposed benchmark is unique in its focus on interpreting complex human instructions and producing multi-step, high-complexity code.
CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning (2025.acl-long)

Copied to clipboard

Challenge: Existing fine-tuning approaches that focus on English-centric training corpora often introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-linguistic interactions.
Approach: They propose a multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level.
Outcome: The proposed model outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods.

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