Papers by Haoran Yang

33 papers
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)

Copied to clipboard

Challenge: Large language models exhibit significant performance discrepancies between high- and low-resource languages.
Approach: They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset.
Outcome: The proposed model achieves consistent multilingual representations across languages.
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025.acl-long)

Copied to clipboard

Challenge: Existing privacy protection methods for large language models suffer from performance degradation or large inference time overhead.
Approach: They propose a plug-and-play method to protect the privacy of user inputs during LLM inference . they use offline restoration vectors to train restoration vector for each privacy span type .
Outcome: The proposed method can prevent the linear growth of the privacy budget.
A Thorough Examination of Decoding Methods in the Era of LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Decoding methods are essential for converting language models from next-token predictors into practical task solvers.
Approach: They propose to evaluate decoding methods in general-purpose large language models . they find that decoding method performance is notably task-dependent .
Outcome: The proposed methods perform task-dependently and are influenced by alignment, model size, and quantization.
CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) generate unreliable responses due to their cognitive alignment of context and intent.
Approach: They propose a benchmark to identify possible implicit assumptions in QA questions . they use retrieved Wikipedia fragments to identify interpretations for a given query .
Outcome: The proposed benchmark identifies possible implicit assumptions and improves answer accuracy by 11.75% . retrieved Wikipedia fragments help identify possible interpretations for a given query .
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Copied to clipboard

Challenge: Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach: They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome: Texar supports machine translation, summarization, dialog, content manipulation, and more.
iMOVE : Instance-Motion-Aware Video Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Video Large Language Models have led to rapid development, significantly enhancing the capture of overall video semantics and achieving remarkable performance in general video understanding tasks.
Approach: They propose a large-scale instance-motion-aware video instruction-tuning dataset iMOVE that utilizes Event-awful Spatiotemporal Efficient Modeling to retain informative instance spatiotemporal motion details while maintaining computational efficiency.
Outcome: The proposed model excels in video temporal understanding and general video understanding.
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach: They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome: The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).
Unveiling the Generalization Power of Fine-Tuned Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, but the comprehensive effects of fine-tuning on the LLMs’ generalization ability are not fully understood.
Approach: They conduct extensive experiments across five distinct language tasks on different datasets to investigate whether fine-tuning affects the generalization ability intrinsic to LLMs.
Outcome: The proposed model can generalize to different domains and tasks by integrating the in-context learning strategy during fine-tuning on generation tasks.
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence.
Approach: They propose a method to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence.
Outcome: The proposed method can generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence.
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking (2025.acl-long)

Copied to clipboard

Challenge: Existing fact-checking methods that use large language models often generate subtle factual errors.
Approach: They propose a fact-checking framework that uses extracted knowledge graphs to enhance text representation.
Outcome: GraphCheck outperforms existing specialized fact-checkers on seven benchmarks spanning general and medical domains . Graph Neural Networks process extracted knowledge graphs as a soft prompt, enabling efficient fact- checking in a single inference call.
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach: They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome: The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.
A Frustratingly Simple Decoding Method for Neural Text Generation (2024.lrec-main)

Copied to clipboard

Challenge: Neural text generation is notorious for repetitive loops and tedious outputs.
Approach: They propose a method that penalizes future generation of repetitive content . they construct an anti-LM based on previously generated text .
Outcome: The proposed method outperforms established baselines in terms of generation quality, decoding speed, and universality.
Language Constrained Multimodal Hyper Adapter For Many-to-Many Multimodal Summarization (2025.acl-long)

Copied to clipboard

Challenge: Existing models that share parameters neglect the language-specific knowledge learning.
Approach: They propose a language-constrained multimodal hyper adapter for multimodal summarization that integrates language-specific adapters into multilingual pre-trained backbones.
Outcome: The proposed model can generate summaries based on multimodal documents such as text and visuals, allowing people to quickly locate key information from the vast multimedia con.
SafeMT: Multi-turn Safety for Multimodal Language Models (2026.acl-long)

Copied to clipboard

Challenge: Multi-turn dialogues pose a greater risk than single prompts, but existing safety benchmarks do not account for this situation.
Approach: They propose a benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images.
Outcome: The proposed model reduces multi-turn Attack Success Rate (ASR) compared to existing guard models.
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations (2025.findings-naacl)

Copied to clipboard

Challenge: a new paradigm for dialogue systems is being developed to mimic human interactions . the current single-step dialogue paradigm lacks the depth and fluidity of human interactions.
Approach: They propose a step-by-step dialogue paradigm that mimics human interactions . they use a dataset to fine-tune existing language models .
Outcome: The proposed system mimics the dynamic nature of human conversations . it is compared with existing paradigms and will be released later this year .
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability .
Approach: They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval .
Outcome: The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets.
TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing RL methods rely on unstructured self-sampling to fit scalar rewards, resulting in inefficient rollouts.
Approach: They propose a structured template-guided RL framework that augments policy optimization with explicit template guidance.
Outcome: Experiments show that TemplateRL outperforms GRPO and GRPI by 99% on AIME and 41% on AMC with superior stability on weak models and remarkable cross-domain generalization.
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach: They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome: The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis (2025.emnlp-main)

Copied to clipboard

Challenge: Existing solutions to fine-tune large language models for domain-specific tasks are ineffective in addressing privacy concerns.
Approach: They propose a privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
Outcome: The proposed framework fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
Exploring Compositional Generalization of Large Language Models (2024.naacl-srw)

Copied to clipboard

Challenge: a recent study has found that large language models can generalize compositional instructions from simple instructions to complex ones.
Approach: They study the generalization ability of large language models with respect to compositional instructions . they first construct a dataset with the help of ChatGPT guided by the self-instruct technique .
Outcome: The proposed model can generalize from simple instructions to more intricate ones, the authors show . their results show that training LLMs on higher-order compositional instructions improves performance on lower-order ones, but not on higher order ones.
Persona-E²: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events (2026.acl-long)

Copied to clipboard

Challenge: A critical bottleneck is the lack of ground-truth human data to link personality traits to emotional shifts.
Approach: They propose a large-scale dataset to capture reader-based emotional variations across news, social media, and life narratives.
Outcome: The proposed model captures reader-based emotional variations across news, social media, and life narratives.
Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: In-context learning (ICL) struggles with complex reasoning due to superficial, example-level implicit imitation.
Approach: They propose an automated method that shifts from surface-level examples to more guidance-oriented thought patterns.
Outcome: The proposed method achieves 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5% accuracy.
Piecing It All Together: Verifying Multi-Hop Multimodal Claims (2025.coling-main)

Copied to clipboard

Challenge: Existing claim verification datasets often do not require systems to perform complex reasoning or effectively interpret multimodal evidence.
Approach: They propose a task that requires models to reason over multiple pieces of evidence . they construct a large-scale dataset comprising 15k multi-hop claims paired with multimodal evidence - generated and refined using large language models with additional input from human feedback.
Outcome: The proposed method is based on human performance benchmarks and human reasoning hops.
HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level (2023.acl-long)

Copied to clipboard

Challenge: Existing research on HKGs rarely models the graphical and sequential structure of HKG, limiting their representation.
Approach: They propose a Hierarchical Attention model for HKG Embedding that includes global-level and local-level attention to model the graphical structure of HKGs.
Outcome: The proposed model achieves state-of-the-art performance on HKG standard datasets and addresses the issue of HKG multi-position prediction for the first time.
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)

Copied to clipboard

Challenge: a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks.
Approach: They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains .
Outcome: a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively .
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Copied to clipboard

Challenge: Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach: They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome: The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.
Rephrasing Invokes Better Generations for Large Language Models (2024.naacl-srw)

Copied to clipboard

Challenge: Existing methods for prompt tuning and input pre-processing are under-studied . e.g., ReLLM replaces low-frequency words with their high-frequency counterparts .
Approach: They propose a method that automatically paraphrases input content for better output generation.
Outcome: The proposed method is user-friendly and requires no additional training.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach: They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome: The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have paved the way for complex tasks such as role-playing.
Approach: They propose a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models.
Outcome: The proposed framework improves role-playing abilities with 168,093 samples.
Bridging the Gap between Pre-Training and Fine-Tuning for Commonsense Generation (2023.findings-eacl)

Copied to clipboard

Challenge: Existing methods focusing on this task usually concatenate the concatened concepts words as the inputs of a pre-trained language model (PLM) however, in pre-training, the input is often corrupted sentences with correct word order.
Approach: They propose a two-stage framework to improve the ability of pre-trained language models to deal with masked sentences with incorrect word order and a special token to make the input distribution more similar to the one used in pre-training.
Outcome: The proposed method is able to generate a sentence containing all given concepts and correctly describe the relations between concepts.
Chain-of-Dictionary Prompting Elicits Translation in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation . yet, they struggle with translating low-resource languages.
Approach: They propose a framework that chained multilingual dictionaries to elicit translation abilities for LLMs . they show that CoD can significantly improve LLM translation by evoking more information .
Outcome: The proposed framework improves on ChatGPT and InstructGPT's translation abilities.
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries (2026.acl-long)

Copied to clipboard

Challenge: a goal of LLM alignment is to balance usefulness with harmlessness, but this conflictes when knowledge serves both legitimate and malicious purposes.
Approach: They propose a framework that combines safety-research contexts with adversarial interactions to exploit a vulnerability in Jargon queries.
Outcome: a framework outperforms existing methods in analyzing Jargon queries, a study shows . it achieves 93% of attacks across seven models, while remaining useful, the authors say .
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Copied to clipboard

Challenge: Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach: They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome: The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.

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