Papers by Jiahao Chen

26 papers
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control (2026.findings-acl)

Copied to clipboard

Challenge: Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, but academic research remains non-reproducible due to the lack of publicly available training data.
Approach: They propose a system for long-form song generation with fine-grained style conditioning that includes a licensed synthetic dataset and a song generation model, Muse.
Outcome: The proposed system achieves competitive performance on phoneme error rate, text–music style similarity, and audio aesthetic quality while enabling controllable segment-level generation across different musical structures.
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Conventional speculative decoding methods use a predefined length policy for proposing drafts, but the reality deviates from this assumption.
Approach: They propose a self-verification length policy that adaptively determines the lengths of draft sequences by referring to the draft entropy.
Outcome: The proposed method achieves 17% speedup on MT-Bench and 22% speedup in long-form reasoning.
MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing models that use English and local languages have a multilingual gap . a language-informed co-reasoning framework can be used to improve multilingual reasoning .
Approach: They propose a language-informed co-reasoning framework that elicits parallel English and local-language reasoning and abstracts them into structured concepts.
Outcome: Experiments show that Med-CoReasoner improves multilingual reasoning performance by 5% . the framework produces clinically sound and culturally grounded reasoning traces .
AesX: Enhance Your Images with Stunning Aesthetic Beauty (2026.acl-industry)

Copied to clipboard

Challenge: Existing models do not analyze human preferences at a finer granularity, which leads to quality issues.
Approach: They propose a set of preference indicators across two major dimensions, text-image consistency and aesthetic quality, and a generative framework to steer the model toward a generation path that more closely aligns with human aesthetic sensibilities.
Outcome: The proposed model improves target recognition accuracy and overall visual aesthetic presentation by focusing on human preferences.
From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)

Copied to clipboard

Challenge: Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time.
Approach: They propose a framework that reframes language modeling as next-state prediction under interaction.
Outcome: The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics .
Circuit Complexity Bounds for RoPE-based Transformer Architecture (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies provide the circuit complexity bounds to Transformer-like architectures. position embedding has emerged as a crucial technique in modern large language models.
Approach: They propose to use position embedding to improve Transformer-like architectures by analyzing their circuits and analyzing the results.
Outcome: The proposed model is able to solve canonical tasks without embedding positional information.
CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations (2022.coling-1)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding.
Approach: They propose a Chinese pre-trained language model that implicitly encodes words into characters . they propose 'contrastive learning over word' and 'character' representations to improve learning .
Outcome: The proposed model can encode words into fine-grained representations without modification of production pipelines.
Localized Low-Rank Adaptation within Clustered Parameter Subspaces (2026.acl-long)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) for large language models has been successful in various domains.
Approach: They propose to perform low-rank updates within clustered parameter subspaces . they group rows/columns of update matrix into locally coherent, uncorrelated subspace blocks .
Outcome: Empirical results show that low-rank Adaptation (LoRA) is better than global adaptations in various domains.
TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models (2025.acl-long)

Copied to clipboard

Challenge: Existing Trojan attacks require extensive training data and poor generalization, limiting effectiveness and scalability.
Approach: They propose a method for embedding Trojans into plugins using a single edit layer . they find that the method reduces modified parameters by 8-fold and cuts injection time to 25 seconds .
Outcome: The proposed method achieves an average attack success rate of 91%, a 78% improvement over the state-of-the-art (SOTA) method.
VIRT: Improving Representation-based Text Matching via Virtual Interaction (2022.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that representation-based text matching methods suffer from performance degradation due to the lack of interactions between the pair of texts.
Approach: They propose a virtual interaction mechanism that enables deep interaction between texts . they propose 'inteRacTion mechanism' that can be integrated into existing methods as plugins .
Outcome: The proposed method outperforms state-of-the-art models on six text matching benchmarks.
Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-augmented generation (RAG) helps by injecting external information, but current methods are costly, generalize poorly, or ignore the model’s internal knowledge.
Approach: They propose a framework to train large language models to leverage both internal and external knowledge sources.
Outcome: The proposed framework outperforms existing methods and achieves efficient retrieval-augmented reasoning.
Dr.ECI: Infusing Large Language Models with Causal Knowledge for Decomposed Reasoning in Event Causality Identification (2025.coling-main)

Copied to clipboard

Challenge: Existing solutions lack generalizability to unseen domains, underscoring the urgent need for generalization capabilities in the field of ECI.
Approach: They propose a multi-agent Decomposed reasoning framework for Event Causality Identification that incorporates specialized agents such as Causal Explorer and Mediator Detector.
Outcome: The proposed framework improves the state-of-the-art performance of LLMs for event causality identification (ECI) tasks compared with baselines based on LLM and supervised training.
Minimal Distillation Schedule for Extreme Language Model Compression (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods for teacher assistant-based distillation require multiple trials to find the optimal teacher assistant.
Approach: They propose a method that allows scheduling of an optimal teacher assistant in just one trial . they show that student performance is positively correlated with the scale-performance tradeoff .
Outcome: The proposed method can select the optimal teacher assistant in just one trial . it can be used to compare performance of student and teacher assistants on GLUE benchmarks.
Lifting the Curse of Capacity Gap in Distilling Language Models (2023.acl-long)

Copied to clipboard

Challenge: Existing studies have shown that pretrained language models require a tremendous amount of inference compute to perform.
Approach: They propose to compress pretrained language models to small ones with a teacher-student paradigm to fill the capacity gap.
Outcome: The proposed model achieves state-of-the-art performance at small FLOPs compared with competitive baselines.
RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank (2023.acl-long)

Copied to clipboard

Challenge: Unsupervised sentence representation learning is one of the fundamental problems in natural language processing . contrastive learning methods fail to capture fine-grained ranking information among the sentences .
Approach: They propose a novel approach for unsupervised sentence representation learning that integrates ranking consistency and ranking distillation with contrastive learning into a unified framework.
Outcome: The proposed approach performs better over state-of-the-art models on STS and TR tasks.
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives (2023.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that combining both proposed methods leads to a gain of 1.8 points compared to the strong baseline SimCSE configured with BERT base.
Approach: They propose a method to deal with dropout noise and a dimension-wise contrastive learning objective to address feature corruption.
Outcome: The proposed method achieves 1.8 points compared to the strong baseline SimCSE and 1.4 points for DiffCSE.
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis (2025.findings-acl)

Copied to clipboard

Challenge: Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own . limited available data and deficient diversity in current datasets hinder study of parody .
Approach: They build a dataset of parody users and annotated comments from both English and Chinese corpora to test parody detection and comment sentiment analysis.
Outcome: The proposed datasets provide richer contextual information, which is lacking in existing datasets.
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention (2026.acl-long)

Copied to clipboard

Challenge: Code Language Models learn attention based on statistical input-output token correlations.
Approach: They propose a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes.
Outcome: The proposed model outperforms baselines in three languages, with gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization.
Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach: They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome: The proposed framework enables agents to tackle unseen software-developing tasks more effectively.
Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods lack explainability and generalization, making it difficult to justify inference decisions and detect implicit sentiment across domains and varied expression patterns.
Approach: They propose an explainable multi-path tree-guided chain-of-thought framework specifically designed for ASQP.
Outcome: Experiments on benchmark datasets show that Tree-CoT-RT outperforms baselines.
SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion (2020.lrec-1)

Copied to clipboard

Challenge: Recent studies show that pre-trained models can learn unsupervised language representations by self-supervised tasks on large-scale corpora.
Approach: They propose a pre-training task called Sentence Insertion for Chinese query-passage pairs NLP tasks . they propose 'word segmentation' method to enhance Chinese Bert performance .
Outcome: The proposed task improves Chinese pre-trained models significantly.
DistillCSE: Distilled Contrastive Learning for Sentence Embeddings (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to sentence embeddings are based on contrastive learning (CL) .
Approach: They propose a framework which performs contrastive learning under the self-training paradigm with knowledge distillation and propose 'Group-P shuffling strategy' and averaging logits from multiple teacher components.
Outcome: The proposed framework outperforms many strong baseline methods and yields a new state-of-the-art performance.
LLMs as Collaborator: Demands-Guided Collaborative Retrieval-Augmented Generation for Commonsense Knowledge-Grounded Open-Domain Dialogue Systems (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to capture the unique knowledge demands of LLMs are unsatisfactory because of their overestimation and lack of knowledge.
Approach: They propose a novel approach to capture the unique knowledge demands for each dialogue context using CoT and RAG methods.
Outcome: The proposed model can capture the unique knowledge demands for each dialogue context and bring higher-quality responses.
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach: They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome: The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.
EfficientQAT: Efficient Quantization-Aware Training for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Quantization-aware training (QAT) is a low-bit training solution that requires substantial training resources.
Approach: They propose an algorithm that reduces memory consumption by low-bit representations with minimal accuracy loss.
Outcome: EfficientQAT achieves 2-bit Llama-2-70B model on single GPU in 41 hours . compared to previous methods, it obtains model with less than 3 points accuracy degradation .
On Synthetic Data for Back Translation (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies on back translation (BT) focus on beam search or random sampling . a new method to generate synthetic data with a backward model is proposed to improve BT performance.
Approach: They propose a method to generate synthetic data to trade off quality and importance factors . back translation (BT) is one of the most significant technologies in NMT research fields .
Outcome: The proposed method outperforms the baseline methods on WMT14 DE-EN, EN-DE, and RU-EN benchmark tasks.

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