Papers by Yuyang Li

21 papers
LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach: They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome: The proposed model achieves comparable performance to standard dense models with more parameters.
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking (2026.acl-long)

Copied to clipboard

Challenge: Existing models with reasoning capabilities suffer from a severe length collapse in open-ended writing .
Approach: They propose a framework that embeds a dynamic plan-write-reflect cycle into the generation process and train a model with interleaved reasoning traces.
Outcome: The proposed framework achieves state-of-the-art performance on long-form benchmarks compared to other models on the same dataset.
Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain (2025.naacl-industry)

Copied to clipboard

Challenge: a conversational AI system that answers standard airport queries and resolves airport terminology is ideal for airports from the top 20 in terms of annual passenger numbers.
Approach: They propose a Conversational AI system that enables staff to communicate with flight systems . the system answers standard airport queries and resolves airport terminology .
Outcome: The proposed system answers standard airport queries and resolves airport terminology, jargon, abbreviations and dynamic questions involving reasoning.
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)

Copied to clipboard

Challenge: Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation.
Approach: They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward.
Outcome: The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench.
Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to improve the mathematical reasoning capabilities of Large Language Models (LLMs) are limited due to the proprietary nature of the data.
Approach: They propose a data synthesis method that generates large-scale mathematical reasoning datasets using lightweight 7B-scale models.
Outcome: The proposed method outperforms existing open-source datasets in both in-domain and out-of-domain evaluations and shows improvements in code reasoning tasks.
CLEAR: A Clinically Grounded Tabular Framework for Radiology Report Evaluation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing metrics lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports.
Approach: They propose a tabular framework with E**xpert-curated labels and an attribute-level comparison for radiology report evaluation (**CLEAR)
Outcome: The proposed framework can extract clinical attributes and provide automated metrics that are strongly aligned with clinical judgment.
DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to integrate lexical knowledge into deep learning models are limited by large-scale dynamic lexicons.
Approach: They propose a plug-in lexicon incorporation approach for BERT based sequence labeling tasks . they adopt word-agnostic tag embeddings to avoid re-training the representation .
Outcome: The proposed framework achieves new SOTA even with large scale lexicons, the authors show . they adopt word-agnostic tag embeddings to avoid re-training the representation .
SelfMix: Robust Learning against Textual Label Noise with Self-Mixup Training (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to handle label noise in text classification tasks are limited to visual data.
Approach: They propose a method to handle label noise in text classification tasks using a Gaussian Mixture Model.
Outcome: The proposed method outperforms baselines on three types of text classification tasks on visual and textual data.
CMD: a framework for Context-aware Model self-Detoxification (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods of text detoxification fail to achieve a decent balance between effectiveness and generation quality.
Approach: They propose a text detoxification framework that pays attention to both context and detoxification process.
Outcome: Experiments on various LLMs show that the proposed framework can yield the best performance compared to baselines.
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Copied to clipboard

Challenge: Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach: They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome: The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.
ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)

Copied to clipboard

Challenge: Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say .
Approach: They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise.
Outcome: Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise .
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing (2023.findings-acl)

Copied to clipboard

Challenge: Existing parsers that convert image captions into scene graphs often suffer from errors and inconsistency.
Approach: They propose a dataset that re-annotates image captions using a new intermediate representation called FACTUAL-MR and a metric to measure scene graph similarity.
Outcome: The proposed parser outperforms existing parsers in terms of faithfulness and consistency on multiple benchmark datasets.
UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing query augmentation methods face knowledge update lag and hallucinations in large language models (LLMs) Existing methods face two key challenges: (1) separation of query augmented and encoding tasks, which hinders information sharing and introduces cumulative errors; (2) difficulty of selecting optimal augmentation strategy for different scenarios.
Approach: They propose a unified framework for query understanding in RAG that integrates internal and external knowledge to enhance query augmentation and encoding tasks.
Outcome: The proposed framework outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering.
Rethinking Negative Instances for Generative Named Entity Recognition (2024.findings-acl)

Copied to clipboard

Challenge: Named Entity Recognition (NER) models are constrained by a pre-defined label set and require extensive human annotations, which limits their flexibility and adaptability to unseen tasks.
Approach: They propose a Generative NER system that shows improved zero-shot performance across unseen entity domains by introducing contextual information and delineating label boundaries.
Outcome: The proposed model outperforms state-of-the-art methods in zero-shot evaluation.
LLMs Can Simulate Standardized Patients via Agent Coevolution (2025.acl-long)

Copied to clipboard

Challenge: Training medical personnel using standardized patients (SPs) remains a complex challenge, necessitating extensive domain expertise and role-specific practice.
Approach: They propose a simulated patient framework that allows patient agents to simulate diagnostic process through multi-turn dialogues.
Outcome: The proposed framework improves over existing reasoning methods by more than 10% in requirement alignment and better human preference after evolving over 200 cases for 10 hours with excellent generalizability.
SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) lack structural information and semantic context to infer missing entities . large language models often lack structural signals to infuse missing entities into knowledge graphs .
Approach: a modular framework integrates structural information and semantic context into a frozen LLM backbone for link prediction.
Outcome: a new framework integrates KG-derived structural information and semantic context to infer missing entities.
Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to few-shot relation classification have limited labeled examples . a prototype encoder from definition and an instance is needed to learn relation instance classification .
Approach: They propose to learn a prototype encoder from relation definition in a way that is useful for relation instance classification.
Outcome: The proposed encoder outperforms state-of-the-art methods on several datasets.
Robust Question Answering against Distribution Shifts with Test-Time Adaption: An Empirical Study (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing work on robustness tuning (RT) methods has found that QA models fail when the test data has a distribution shift compared to the training data.
Approach: They propose to use test-time adaptation methods to improve QA models after deployment to evaluate their model against text corruption and changes in language and domain.
Outcome: The proposed method improves TTA to be more robust to variation in hyper-parameters and test distributions over time.
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals .
Approach: They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation.
Outcome: The proposed method mitigates behavior collapse and improves performance across benchmarks.
ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents (2026.acl-long)

Copied to clipboard

Challenge: Rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support.
Approach: They propose a peer review benchmarking tool based on paper-specific rubrics and a rubric-guided framework that decomposes reviewing into drafting and grounding stages.
Outcome: The proposed framework outperforms baselines with stronger/larger backbones in both alignment with human judgments and rubric-based review quality across 8 dimensions.
Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression (2026.findings-acl)

Copied to clipboard

Challenge: Despite advances in aligning LLMs with human values, current safety mechanisms remain vulnerable to jailbreak attacks.
Approach: They propose a black-box jailbreak method that uses logical expression translation to bypass LLM safety mechanisms.
Outcome: The proposed method exploits the distributional gap between alignment data and logic-expressed inputs while preserving the underlying semantic intent and readability while evading safety constraints.

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