Papers by Zhijing Zhang

12 papers
Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought prompting.
Approach: They examine the factors influencing CoT distillation including granularity, format and teacher model.
Outcome: The proposed model is based on four teacher models and seven student models across seven mathematical and commonsense reasoning datasets.
SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches focus on general utility metrics, overlooking the preservation of semantically related concepts.
Approach: They propose a method that introduces self-generated proximal visual tokens to prevent forgetting vulnerability.
Outcome: The proposed framework outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning.
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf (2026.acl-demo)

Copied to clipboard

Challenge: Emerging AI-powered writing assistants focus on grammar fixes or simulating peer review with final scores, yet they fall short of providing concrete, actionable suggestions that help students improve their papers during drafting.
Approach: They propose a human-centered writing assistant system that delivers actionable suggestions as Overleaf-native inline comments while leaving the actual writing entirely to human authors.
Outcome: The proposed system outperforms a baseline with the skill library and provides actionable suggestions while leaving the actual writing to human authors.
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST) (2025.findings-acl)

Copied to clipboard

Challenge: Despite advances in machine translation, domain-specific terminology translation remains challenging.
Approach: They propose a large-scale multilingual AI terminology dataset that combines LLMs for extraction with human expertise for translation.
Outcome: The proposed framework combines human translation expertise with LLMs to improve translation accuracy and improve BLEU and COMET scores.
Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure .
Approach: They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness.
Outcome: Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure .
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation (2020.coling-main)

Copied to clipboard

Challenge: a large-scale, general-domain dataset is needed for knowledge graph-to-text generation . data collection is expensive and data-intensive, making it difficult to get good annotation .
Approach: They propose to use a large-scale, general-domain dataset to generate unsupervised text from knowledge graphs.
Outcome: The proposed dataset has 1.3M text and graph examples, and is a benchmark for future research . good annotation is expensive and difficult to get, and it's difficult to check quality .
Test of Time: Rethinking Temporal Signal of Benchmark Contamination (2026.acl-long)

Copied to clipboard

Challenge: Existing work on benchmarks containing publicly available information has been interpreted as a temporal signal for benchmark contamination.
Approach: They show that LLM-transformed questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same documents.
Outcome: The proposed model can produce different temporal patterns compared to fill-in-the-blank questions retrieved from the same documents.
Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering (2026.findings-acl)

Copied to clipboard

Challenge: Existing retrieval-augmented approaches focus on ignoring the structural information of the Knowledge Base (KB) and the question.
Approach: They propose a structure-aware subgraph retrieval stage that ranks candidate subgraphs by aligning them with the question’s structure, along with semantic relevance.
Outcome: Experiments on GrailQA, WebQSP, and GraphQuestions show that the proposed framework achieves state-of-the-art performance.
Analyzing the Role of Semantic Representations in the Era of Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Existing studies show the benefits of semantic representations in NLP tasks . Existing work using AMR is concerned with trainable models .
Approach: They propose an AMR-driven chain-of-thought prompting method that uses AMR . they propose to use it to predict which input examples AMR may help or hurt on .
Outcome: The proposed method hurts performance more than it helps on five different tasks.
CausalNLP Tutorial: An Introduction to Causality for Natural Language Processing (2022.emnlp-tutorials)

Copied to clipboard

Challenge: Establishing causal relationships is a fundamental goal of scientific research . lack of clear definitions, notations, benchmark datasets, and challenges remains .
Approach: They introduce the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provide an overview of causal perspectives to NLP problems.
Outcome: This tutorial introduces the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provides an overview of causal perspectives to NLP problems.
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis (2020.emnlp-main)

Copied to clipboard

Challenge: Existing ABSA test sets cannot be used to distinguish the sentiment of the target aspect from the non-target aspect.
Approach: They propose a simple but effective approach to enrich ABSA test sets by disentangle the confounding sentiments of non-target aspects from the target aspect’s sentiment.
Outcome: The proposed model can distinguish the sentiment of the non-target aspects from the target aspect’s sentiment by using the Aspect Robustness Test Set (ARTS).
CompKBQA: Component-wise Task Decomposition for Knowledge Base Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge base question answering methods struggle with complex queries.
Approach: They propose a framework that optimizes the process of fine-tuning a LLM for generating logical forms by enabling it to learn relevant sub-tasks like skeleton generation, topic entity generation, and relevant relations generation.
Outcome: The proposed framework achieves state-of-the-art on two benchmark KBQA datasets, WebQSP and CWQ.

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