Papers by Yequan Wang

22 papers
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs (2026.acl-long)

Copied to clipboard

Challenge: Recent self-training approaches have reduced reliance on human-labeled data, which limits their scalability.
Approach: They propose a team-based self-play algorithm that iteratively refines alignment without additional human supervision.
Outcome: The proposed algorithm outperforms baselines and LLM benchmarks in the self-supervised setting.
Multimodal Reasoning with Multimodal Knowledge Graph (2024.acl-long)

Copied to clipboard

Challenge: Multimodal reasoning with large language models (LLMs) often suffers from hallucinations and the presence of deficient or outdated knowledge within LLMs.
Approach: They propose a multimodal reasoning method that leverages multimodal knowledge graphs to learn rich and semantic knowledge across modalities.
Outcome: The proposed method outperforms state-of-the-art models on multimodal question answering and multimodal analogy reasoning tasks while training on only a small fraction of parameters.
Reflection on Knowledge Graph for Large Language Models Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for supplementing Large Language Models (LLMs) with knowledge graphs often introduce noise in the retrieval and reasoning pipeline, hindering their ability to integrate external knowledge for complex multi-hop question answering.
Approach: They propose a framework to enhance LLMs' reasoning capabilities through reflective engagement with knowledge graphs by Query Decoupling, LLM-Driven Knowledge Graph Exploration, and Inference with Knowledge Reconstruction.
Outcome: The proposed framework integrates external knowledge into LLMs and trains them to leverage this knowledge for answering questions.
Rethinking Document-Level Relation Extraction: A Reality Check (2023.findings-acl)

Copied to clipboard

Challenge: Recent efforts push up performance boundaries of document-level relation extraction (DocRE) but these efforts are not promising.
Approach: They construct four types of entity mention attacks to examine model robustness . they also have a close check on model usability in a more realistic setting .
Outcome: The proposed model is based on a strong or untenable assumption in common . the model is robust under four types of mention attacks and usable in a realistic setting .
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction (2022.coling-1)

Copied to clipboard

Challenge: Existing solutions for quotation extraction use rule-based approaches and sequence labeling models.
Approach: They propose a Context and Former-Label Enhanced Net for quotation extraction.
Outcome: The proposed method achieves state-of-the-art performance on complicated quotation extraction on two public datasets and one proprietary dataset.
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) fail to capture these dynamics, focusing on static, open-ended evaluations.
Approach: They propose a benchmark to assess lifelong learning in large language models . they use two episodic datasets rich in narrative structure and character interactions .
Outcome: Experiments on LLMs show that non-parametric methods outperform parametric ones in managing stateful learning.
ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Copied to clipboard

Challenge: Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach: They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome: The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.
Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing continual learning paradigms prioritize instant performance through dense updates, leading to catastrophic forgetting and rapid exhaustion of model capacity.
Approach: They propose a method that preserves previously acquired knowledge and acquires new task-specific skills while preserving sufficient parameter capacity for subsequent adaptation.
Outcome: The proposed method is based on the brain's functional partitioning and can be used to map tasks between specialized and generalist neurons.
Break Through the Compression Bottleneck: From Theory to Practice (2026.findings-acl)

Copied to clipboard

Challenge: Existing compression methods suffer from bottleneck issues when compression ratio is increased.
Approach: They propose a novel approach to combine low-rank decomposition and quantization methods to reduce the compression bottleneck.
Outcome: The proposed method reduces the computational and memory overhead of existing methods while maintaining model accuracy.
Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) has become a standard paradigm for grounding Large Language Models (LLMs) however, performance degrades substantially when faced with noisy, outdated, or conflicting retrieved information.
Approach: They propose a framework that explicitly elicits the model’s parametric knowledge as prior information to guide reasoning on retrieved documents.
Outcome: The proposed framework achieves robust performance across varying degrees of external inconsistency and noise.
Theory-optimal Quantization Based on Flatness (2026.acl-long)

Copied to clipboard

Challenge: Recent approaches to quantization of Large Language Models (LLMs) have been widely adopted due to activation outliers, which degrade model performance especially at lower bit precision.
Approach: They propose a new metric for quantization that strategically distributes outlier magnitudes across matrix dimensions via optimized diagonal operations.
Outcome: The proposed framework achieves less than 1% accuracy drop in W4A4 quantization on the LLaMA-3-8B model and reduces the performance gap by 39.1% on the more challenging W2A4KV16 model.
Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency (2025.findings-acl)

Copied to clipboard

Challenge: Recent dynamic computation methods show that not all components are required for inference, enabling a training-free pipeline.
Approach: They propose a token-position aware layer skipping framework to save 1.5x times operations efficiently while maintaining performance.
Outcome: The proposed algorithm achieves 1.5x speedup on large language models with no retraining and with comparable performance on the GSM8K and BBH benchmarks.
Improving Zero-shot LLM Re-Ranker with Risk Minimization (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are effective Query Likelihood Models, but their estimation is biased and the model's accuracy is poor.
Approach: They propose a framework which leverages Bayesian decision theory to quantify and mitigate this bias.
Outcome: The proposed framework improves re-ranking, especially in improving the Top-1 accuracy.
Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states.
Approach: They propose a method that enhances the utilization of contextual knowledge within LLMs’ internal representations by employing V-usable information analysis.
Outcome: The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge.
Commonsense Knowledge Editing Based on Free-Text in LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge editing methods focus on editing triple-based facts such as entity-relation pairs and events (multiple triplets).
Approach: They propose a Knowledge Localization for Free-Text method which uses a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge and a knowledge editing module to update knowledge.
Outcome: The proposed method exploits the potential of the MLP and Attention layers and edits commonsense knowledge based on free-text.
CORT: A New Baseline for Comparative Opinion Classification by Dual Prompts (2022.findings-emnlp)

Copied to clipboard

Challenge: Comparative opinion classification is a common linguistic phenomenon.
Approach: They propose a framework for comparative opinion classification using embedded knowledge in pre-trained language models.
Outcome: The proposed framework delivers state-of-the-art and robust performance on all benchmark datasets.
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a cornerstone in artificial intelligence due to their exceptional performance.
Approach: They propose a training-free approach that integrates existing MLLMs for effective multimodal expansion while retaining their original performance.
Outcome: The proposed approach can expand LLMs' multimodal capabilities while retaining original performance.
Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint (2024.findings-acl)

Copied to clipboard

Challenge: Existing decoding methods for large language models (LLMs) are specialized in resolving knowledge conflicts and could inadvertently deteriorate performance in absence of conflicts.
Approach: They propose an adaptive decoding method to discern whether knowledge conflicts occur and resolve them by a contextual information-entropy constraint decoding technique.
Outcome: The proposed method improves the model’s faithfulness to conflicting context and maintains high performance among non-conflicting contexts.
EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)

Copied to clipboard

Challenge: Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance.
Approach: They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors.
Outcome: The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios.
Knowledgeable Parameter Efficient Tuning Network for Commonsense Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Existing commonsense question answering models incur prohibitive computation costs and poor interpretability .
Approach: They propose a parameter efficient tuning network to pair PLMs with external knowledge for commonsense question answering.
Outcome: The proposed adapter integrates entity- and query-related knowledge at a small cost.
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict (2022.findings-naacl)

Copied to clipboard

Challenge: Sarcasm employs ambivalence, where one says something positive but actually means negative . linguistically, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit .
Approach: They propose a Dual-Channel Framework to model literal and implied sentiments separately . they propose sarcastic networks that can detect sarcasm sentiments in political debates .
Outcome: The proposed framework achieves state-of-the-art on political debates and Twitter datasets.
Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Continual Learning (CL) for Large Language Models faces a fundamental Stability-Plasticity Dilemma . Rank-Blindness enforces a single rank constraint across diverse tasks, leading to catastrophic forgetting of earlier tasks and underfitting on complex new ones.
Approach: They propose a rank-spectrum-based rehearsal-free framework that explicitly disentangles knowledge into two orthogonal subspaces.
Outcome: The proposed framework achieves a superior stability-plasticity balance compared to single-rank baselines.

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