Papers by Yun Huang

25 papers
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)

Copied to clipboard

Challenge: Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target.
Approach: They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success.
Outcome: The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design.
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs (P19-1)

Copied to clipboard

Challenge: Existing models to tackle multi-hop reading comprehension (RC) are focusing on a single document or paragraph, but they lack the ability to do reasoning across multiple documents.
Approach: They propose a heterogeneous document-entity graph with different types of nodes and edges to solve multi-hop RC problem.
Outcome: The proposed model can do reasoning over the proposed graph with nodes representation initialized with co-attention and self-attention based context encoders.
Advancing Collaborative Debates with Role Differentiation through Multi-Agent Reinforcement Learning (2025.acl-long)

Copied to clipboard

Challenge: Multi-agent collaborative tasks exhibit exceptional capabilities in natural language applications and generation.
Approach: They propose a multi-LLM Cooperation framework with automatic role assignment capabilities that allows multiple agents to embed roles in turn-based speaking.
Outcome: The proposed framework improves collaboration and expertise among agents and teams by enabling them to share roles and develop complementary strengths from the optimization level.
Meta-Reflection: A Feedback-Free Reflection Learning Framework (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to improve large language models' ability to understand and reason are limited by external feedback.
Approach: They propose a feedback-free reflection mechanism that requires only a single inference pass without external feedback.
Outcome: The proposed method is based on an industrial e-commerce benchmark and public datasets.
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)

Copied to clipboard

Challenge: Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards.
Approach: They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates.
Outcome: The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods.
Composite Backdoor Attacks Against Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated superior performance on various tasks, but untrustworthy third-party LLMs may covertly introduce vulnerabilities for downstream tasks.
Approach: They propose a composite backdoor attack that scatters multiple trigger keys in different prompt components.
Outcome: The proposed attack achieves 100% Attack Success Rate (ASR) with a False Triggered Rate (FTR) below 2.06% and negligible model accuracy degradation.
Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process.
Approach: They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors.
Outcome: The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs.
Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios.
Approach: They propose a Multi-agent Legal Simulation Driver to generate synthetic data by simulating interactive legal scenarios.
Outcome: The proposed framework ensures consistency of legal attributes between participants and introduces a supervisory mechanism to align participants’ characters and behaviors as well as addressing distractions.
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation (2026.acl-long)

Copied to clipboard

Challenge: Multimodal large language models have advanced rapidly, yet most remain English-centric . scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of non-English image–text supervision.
Approach: They propose a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone.
Outcome: The proposed framework achieves competitive performance with a fully multimodally trained model using less than 2% of the text data.
FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios (2026.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs) are prone to misuse and misinformation, posing serious compliance risks.
Approach: They propose a bilingual red-teaming benchmark to test an LLM’s refusal of requests that violate financial compliance.
Outcome: The proposed benchmark is based on real-world financial crime cases and ethical violations and includes 14 subcategories covering financial crimes and ethical breaches.
Toward Automated Robustness Evaluation of Mathematical Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing robustness evaluations rely on hand-crafted templates or a limited set of perturbation rules, resulting in model failure.
Approach: They propose a framework inspired by software stress testing that generates adversarial variants via a multi-round rewrite-verify loop, ensuring semantic consistency while successfully inducing model failure.
Outcome: The proposed framework generates adversarial variants dynamically for each LLM, minimizing the risk of data contamination.
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge (2020.emnlp-main)

Copied to clipboard

Challenge: Paraphrase identification requires specialized domain knowledge to perform . state-of-the-art neural models and non-expert human annotators have poor performance on PARADE .
Approach: They propose a benchmark dataset called PARADE for paraphrase identification that requires specialized domain knowledge.
Outcome: The proposed dataset shows state-of-the-art models and non-expert human annotators have poor performance on PARADE.
LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs (2025.acl-long)

Copied to clipboard

Challenge: TrickCatcher generates test cases that pass existing tests yet contain bugs . a recent study found that tricky bugs are not detected by test suites .
Approach: They propose an LLM-powered approach to generating test cases for uncovering bugs in plausible programs . they use a PUT and specification to generate program variants, an input generator and an Llm to construct test inputs .
Outcome: The proposed approach achieves recall, precision, and F1 scores that are 1.80, 2.65, and 1.66 . trickCatcher generates program variants based on the program under test and its specification .
TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration (2025.emnlp-main)

Copied to clipboard

Challenge: Multimodal in-context learning (ICL) is a key mechanism for harnessing the capabilities of large vision–language models.
Approach: They propose a transformer-based model with task-aware attention that dynamically configures ICL sequences.
Outcome: Experiments on five LVLMs and nine datasets show that TACO surpasses baselines across diverse ICL tasks.
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach: They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome: The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.
Reference-based Metrics Disprove Themselves in Question Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing metrics for question generation are based on human-written references . however, the results of the metrics on our study disprove the metrics themselves .
Approach: They propose to use human-written references to evaluate question generation . they propose to combine criteria such as naturalness, answerability, and complexity .
Outcome: The proposed model is based on multi-dimensional criteria such as naturalness, answerability, and complexity, utilizing large language models.
Distorted or Fabricated? A Survey on Hallucination in Video LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Despite significant advances in video-language modeling, hallucinations remain a persistent challenge in video large language models.
Approach: They present a systematic taxonomy that categorizes hallucinations into two core types: dynamic distortion and content fabrication.
Outcome: The proposed taxonomy categorizes hallucinations into two core types: dynamic distortion and content fabrication.
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding (2020.acl-main)

Copied to clipboard

Challenge: Existing knowledge graph embeddings have improved the knowledge graph link prediction task, but complex relations such as N-to-1, 1-to-N and N- to-N remain challenging to predict.
Approach: They propose to extend RotatE from 2D complex domain to high dimensional space with orthogonal transforms to model relations.
Outcome: The proposed method improves on N-to-1, 1-to-N and N- to-N cases while maintaining the capability for modeling symmetric/anti-symmetric, inverse and compositional relations.
D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition (2025.emnlp-main)

Copied to clipboard

Challenge: Existing training-free adaptation frameworks for video large language models are limited by the scarcity of high-quality video-text data.
Approach: They propose a training-free adaptation framework that incorporates dynamic compression and question decomposition to address perception bottleneck and token overload.
Outcome: The proposed framework improves video understanding across various benchmarks and on long-video benchmarks.
SportQA: A Benchmark for Sports Understanding in Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: SportQA is a benchmark specifically designed for evaluating Large Language Models (LLMs) sports knowledge is characterized by its fast pace, variety of types, abundance of strategies, and rich player narratives .
Approach: They propose a benchmark specifically designed for evaluating Large Language Models in the context of sports understanding.
Outcome: The proposed benchmark aims to bridge the gap between existing and specialized benchmarks in sports understanding.
JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies have introduced legal theories into LLM workflows to improve their understanding of legal texts and reasoning accuracy.
Approach: They evaluate an expert-annotated four-element knowledge base covering 155 criminal charges.
Outcome: The proposed model can be used to analyze criminal charges and retrieve them in legal cases.
FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach: They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome: The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.
Proofread: Fixes All Errors with One Tap (2024.acl-demos)

Copied to clipboard

Challenge: Extensive experiments on a human-labeled golden set showed our tuned PaLM2-XS model achieved 85.56% good ratio.
Approach: They propose a two-stage tuning approach to acquire the dedicated Large Language Model for the feature, followed by a reinforcement learning approach for targeted refinement.
Outcome: The proposed model achieves 85.56% good quality on Rewrite and proofread tasks on human-labeled golden sets.

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