Papers by Zhijiang Guo

29 papers
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach: They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome: The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
DebateQA: Evaluating Question Answering on Debatable Knowledge (2026.findings-eacl)

Copied to clipboard

Challenge: Existing QA benchmarks that provide fixed answers to debatable questions are inadequate for evaluating their performance.
Approach: They propose to use a dataset of 2,941 debatable questions to assess their ability to provide comprehensive answers to inherently debatably asked questions.
Outcome: The proposed model performs well on 2,941 debatable questions accompanied by human-annotated partial answers that capture a variety of perspectives.
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on detecting LLM’s confidence via statistical uncertainty.
Approach: They propose to use a representation perspective to solve adaptive RAG by enabling dynamic retrieval during generation and enabling retrieval only when the query exceeds LLM's internal knowledge.
Outcome: The proposed framework is superior to existing adaptive RAG methods on a diverse set of tasks.
Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation (2020.emnlp-main)

Copied to clipboard

Challenge: AMR-to-text generation is used to transduce Abstract Meaning Representation structures (AMRs) Graph Convolution Networks (GCNs) are not able to capture non-local information and follow a local (first-order) information aggregation scheme.
Approach: They propose a dynamic fusion mechanism that captures richer non-local interactions . they propose weight tied convolutions and group graph convolution to reduce memory usage .
Outcome: The proposed model outperforms state-of-the-art models on two benchmark datasets with significantly fewer parameters while maintaining the model capacity.
Do We Need Language-Specific Fact-Checking Models? The Case of Chinese (2024.emnlp-main)

Copied to clipboard

Challenge: Existing fact-checking models in other languages lack grounding in real-world claims . current models are constrained to a single domain, like COVID-19 .
Approach: They propose a Chinese document-level evidence retriever that can be translated into Chinese . they then construct an adversarial dataset that is more robust toward biases .
Outcome: The proposed method outperforms translation-based methods and multilingual language models and is more robust toward biases.
CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking (2022.naacl-main)

Copied to clipboard

Challenge: CHEF dataset provides evidence retrieval over non-English claims . e-fact-checking is a time-consuming task, which can take journalists several hours or days.
Approach: They construct a dataset of 10K real-world claims that is based on annotated evidence retrieved from the Internet.
Outcome: The proposed dataset provides evidence retrieval as a latent variable and can be used to train and reason over non-English claims.
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)

Copied to clipboard

Challenge: Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers.
Approach: They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification.
Outcome: The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification.
When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for o1-level performance focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning patterns.
Approach: They construct a reverse reasoning dataset and examine how it is supervised . they find that naively mixing forward and reverse data during SFT weakens the directional distinction .
Outcome: The proposed model improves accuracy by 1.6%–6.8% over a standard model.
Multimodal Automated Fact-Checking: A Survey (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on automated fact-checking focus on text, but they focus on a single modality, text . multimodal misinformation is perceived as more credible by humans and spreads faster than text-only counterparts.
Approach: They propose a framework for automated fact-checking that includes subtasks unique to multimodal misinformation.
Outcome: The proposed framework includes subtasks unique to multimodal misinformation.
TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown significant potential in assisting peer review, but current methods struggle to generate thorough and insightful reviews while maintaining efficiency.
Approach: They propose a framework that models paper review as a hierarchical and bidirectional question-answering process.
Outcome: The proposed framework outperforms baselines on full review generation and actionable feedback comments generation tasks while reducing LLM token usage by up to 80% compared to computationally intensive approaches.
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for directional consistency alignment of large language models are limited . a recent study suggests reverse supervision as a complement to forward reasoning .
Approach: They propose a framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons.
Outcome: The proposed framework achieves 3.2% accuracy improvement across five benchmarks and multiple datasets.
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach: They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome: The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
A Survey on Automated Fact-Checking (2022.tacl-1)

Copied to clipboard

Challenge: Fact-checking is an essential task in journalism due to the speed with which information and misinformation can spread in the media ecosystem.
Approach: They propose to use natural language processing to automate fact-checking by identifying common concepts and defining definitions.
Outcome: The proposed method can predict the veracity of claims using natural language processing, machine learning, and databases.
UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Copied to clipboard

Challenge: Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach: They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome: The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.
Uncovering Main Causalities for Long-tailed Information Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Information Extraction (IE) aims to extract structural information from unstructured texts.
Approach: They propose a framework that aims to uncover the main causalities behind data in the view of causal inference.
Outcome: The proposed framework can detect the main causalities behind data in the view of causal inference.
Better Transition-Based AMR Parsing with a Refined Search Space (D18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsers require a pipeline approach to learn concepts and relationships.
Approach: They propose to use a transition-based search space to conduct a new compact AMR graph and an improved oracle to perform the search.
Outcome: The proposed system achieves the state-of-the-art performance on various datasets with minimal additional information.
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for document-level relation extraction capture non-local interactions but are not able to capture rich non-linguistic interactions.
Approach: They propose a document-level relation extraction model that empowers relational reasoning across sentences by automatically inducing the latent document- level graph.
Outcome: The proposed model achieves an F1 score of 59.05 on a large-scale document-level dataset (DocRED), significantly improving over the previous results.
ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts (2025.emnlp-main)

Copied to clipboard

Challenge: Scientific fact-checking has largely focused on textual and tabular sources, neglecting scientific charts.
Approach: They propose a benchmark for scientific fact-checking grounded in scientific charts . climateViz comprises 49,862 claims paired with 2,896 visualizations . results show current models struggle to perform fact- checking when statistical reasoning is required .
Outcome: The climateviz benchmark is the first large-scale benchmark for scientific fact-checking . it includes 49,862 claims paired with 2,896 visualizations labeled as support, refute, or not enough .
FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment.
Approach: They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling .
Outcome: The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines.
ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing evaluation methods for large language models are labor-intensive and lack efficiency.
Approach: They propose a framework dedicated to assessing long-text generation that includes in-depth human-curated meta-questions spanning various domains . they use a set of proxy-quests with pre-annotated answers to assess the content's quality by incorporating the generated texts as contextual background.
Outcome: The proposed framework assesses the quality of long-text content by matching it with references through human evaluation or automated metrics.
Knowledge Conflicts for LLMs: A Survey (2024.emnlp-main)

Copied to clipboard

Challenge: This survey examines knowledge conflicts for large language models (LLMs) this survey aims to shed light on strategies for improving the robustness of LLMs .
Approach: They focus on three categories of knowledge conflicts: context-memory, inter-context, and intra-membry conflict.
Outcome: The findings highlight the challenges faced by large language models when blending contextual and parametric knowledge.
DVD: Dynamic Contrastive Decoding for Knowledge Amplification in Multi-Document Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) generate information with hallucinations due to uneven retrieval quality and irrelevant contents.
Approach: They propose a decoding strategy which dynamically amplifies knowledge from selected documents during the generation phase.
Outcome: The proposed method outperforms other decoding strategies on ALCE-ASQA, NQ, TQA and PopQA benchmarks.
Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach: They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome: The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are revolutionizing mobile intelligence, but their implementation on mobile devices is severely bottlenecked by the prohibitive resource demands of LLMs.
Approach: They propose a paradigm that forgoes end-to-end updates in favor of a sequential, layer-by-layer manner.
Outcome: Extensive experiments on multiple benchmarks demonstrate the superiority of ChainFed over existing methods, boosting average accuracy by up to 46.46%.
Scene Graph Modification as Incremental Structure Expanding (2022.coling-1)

Copied to clipboard

Challenge: Scene graphs are used in cross-modal tasks such as image retrieval, image captioning, and visual question answering.
Approach: They propose a model that iterates between nodes prediction and edges prediction . they frame scene graph modification as a graph expansion task by introducing incremental structure expanding .
Outcome: The proposed model surpasses the state-of-the-art model by large margins on four benchmarks.
Attention Guided Graph Convolutional Networks for Relation Extraction (P19-1)

Copied to clipboard

Challenge: Existing approaches for selecting relevant partial dependency structures may not yield optimal results.
Approach: They propose a model which directly takes full dependency trees as inputs and uses them to selectively attend to relevant sub-structures.
Outcome: The proposed model can be understood as a soft-pruning approach that automatically learns how to selectively attend to the relevant sub-structures useful for the relation extraction task.
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) excel in tasks ranging from image captioning to complex reasoning.
Approach: They propose a contrastive decoding framework that dynamically calibrates each token generation by mining the model’s internal perceptual discrepancies.
Outcome: The proposed framework mitigates hallucination while enhancing general reasoning capabilities.
LONG2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall (2024.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) is a promising approach to address limitations of fixed knowledge in large language models.
Approach: They propose a benchmark and a metric to assess LLMs' ability to generate long-form responses that exploit retrieved information.
Outcome: The proposed benchmarks lack a comprehensive evaluation method to assess LLMs' ability to generate long-form responses that effectively exploits retrieved information.
Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis (2023.acl-short)

Copied to clipboard

Challenge: Existing retrieval-augmented approaches focus on modeling the retrieved textual knowledge but this may not be able to accurately identify complex relations.
Approach: They propose to retrieve multimodal relation extraction information based on object, sentence, and whole image . they propose to synthesize the object-level, image-level and sentence-level information .
Outcome: The proposed method outperforms state-of-the-art models on multimodal relation extraction.

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