Papers by Yao Yan

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Challenge:	Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one.
Approach:	They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model.
Outcome:	The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs.

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

An Auxiliary Task Boosted Multi-task Learning Method for Service Account Retrieval with Limited Human Annotation (2023.emnlp-industry)

Copied to clipboard

Yuanzhou Yao, Zhao Zhang, Kaijia Yang, Huasheng Liang, Qiang Yan, Yongjun Xu

Semantic Text Processing

Challenge:	Existing approaches to service account retrieval have limited human annotation, resulting in labor-intensive and time-consuming tasks.
Approach:	They propose an Auxiliary task Boosted Multi-Task Learning method which introduces multiple auxiliary tasks and enhances the performance of the main task, service account retrieval.
Outcome:	The proposed method improves the performance of the main task, service account retrieval.

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

Reasoning

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models (2026.findings-acl)

Copied to clipboard

Yixu Wang, Xin Wang, Yang Yao, Xinyuan Li, Xibang Yang, Yan Teng, Xingjun Ma, Yingchun Wang

Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Challenge:	Existing static safety evaluation methods are ill-equipped to address dynamic nature of AI risks and evolving regulations, creating a critical safety gap.
Approach:	They propose a new paradigm of agentic safety evaluation reframing evaluation as a continuous and self-evolving process rather than a one-time audit.
Outcome:	The proposed framework shows a consistent decline in model safety as the evaluation hardens.

Copied to clipboard

Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)

Challenge:	Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach:	They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome:	The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .

Copied to clipboard

Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum

Reasoning

Challenge:	Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window.
Approach:	They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window.
Outcome:	The proposed model scales to multi-million-token effective TTC without exceeding context limits.

On the Abstractiveness of Neural Document Summarization (D18-1)

Copied to clipboard

Fangfang Zhang, Jin-ge Yao, Rui Yan

Text Generation

Challenge:	Recent studies show that document summarization systems are abstractive . authors suggest that automated summarizing systems could be improved .
Approach:	They propose to use a pure copy system to verify abstractiveness of document summarization systems.
Outcome:	The proposed system produces abstractive summaries while being far more efficient.

2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition (2023.findings-emnlp)

Copied to clipboard

Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan Gao, Shusen Wang, Yao Hu, Yiqing Lin

Low-Resource NLP

Challenge:	Named Entity Recognition (NER) tasks are a fundamental task of natural language processing (NLP).
Approach:	They propose a text-to-text framework for Few-Shot Named Entity Recognition (NER) that employs instruction finetuning and auxiliary tasks to enhance the model's understanding of entity types in the overall semantic context of a sentence.
Outcome:	The proposed framework outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art NER algorithms.

Improving Alignment in LVLMs with Debiased Self-Judgment (2025.findings-emnlp)

Copied to clipboard

Sihan Yang, Chenhang Cui, Zihao Zhao, Yiyang Zhou, Weilong Yan, Ying Wei, Huaxiu Yao

Responsible & Trustworthy NLP

Challenge:	Existing methods for aligning LVLMs rely on external datasets, human annotations or complex post-processing.
Approach:	They propose a method that generates a debiased self-judgment score for LVLMs . this self-evaluation metric is created internally by the model without external resources .
Outcome:	The proposed approach outperforms existing methods in reducing hallucinations and safety concerns.

Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition (2026.acl-long)

Copied to clipboard

Yan Fang, Jun Chen, Yian Yao, Shuxin Zhong, Min Sun, Kaishun Wu

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)

Challenge:	Severe acoustic degradation results in unreliable ASR outputs . et al., 2024b): critical concerns regarding reliability and fairness of ASR .
Approach:	They propose a multimodal framework that reframes ASR as semantics-guided speech reconstruction.
Outcome:	The proposed framework achieves an average reduction in WER while also attaining 98.71% BERTScore and 96.7% USE over advanced baselines.

Copied to clipboard

Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao

Challenge:	Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation.
Approach:	They propose a method that compresses the KV cache by layer-wise retaining crucial context.
Outcome:	The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction .

MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation (2023.emnlp-main)

Copied to clipboard

Zexue He, Yu Wang, An Yan, Yao Liu, Eric Chang, Amilcare Gentili, Julian McAuley, Chun-Nan Hsu

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Challenge:	Existing medical datasets require high quality domain-specific datasets.
Approach:	They propose a multi-level, multi-task, and multi-domain medical benchmark to facilitate the development of language models for healthcare.
Outcome:	The proposed model provides granular potential usage and supports a wide range of tasks.

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

Responsible & Trustworthy NLP

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Semantic Relation-aware Difference Representation Learning for Change Captioning (2021.findings-acl)

Copied to clipboard

Yunbin Tu, Tingting Yao, Liang Li, Jiedong Lou, Shengxiang Gao, Zhengtao Yu, Chenggang Yan

Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)

Challenge:	Existing methods to describe semantic change in images with distractors are difficult to learn .
Approach:	They propose a semantic relation-aware difference representation learning network to explicitly learn the difference representation in the existence of distractors.
Outcome:	The proposed network achieves state-of-the-art performance on CLEVR-Change and Spot-the -Diff datasets.

Copied to clipboard

Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

Information Retrieval

Challenge:	Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios .
Approach:	They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets .
Outcome:	The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files.

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Copied to clipboard

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

Probing the Safety Robustness of LLMs in Latent Space (2026.acl-long)

Challenge:	Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach:	They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome:	The proposed method achieves a superior balance between downstream learning and general capability retention.

Copied to clipboard

Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Xin Wang, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang

Robustness in NLP

Challenge:	Despite substantial progress in safety alignment techniques, aligned large language models can still produce unsafe responses under minor internal perturbations.
Approach:	They introduce Activation Steering Attack (ASA) and leverage the Negative Log-Likelihood (NLL) as a diagnostic signal to probe the local sensitivity of safety behaviors in latent space.
Outcome:	The proposed method is model-agnostic and supervision-free, enabling a general and reproducible diagnostic metric for analyzing safety robustness.

EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation (2025.findings-emnlp)

Copied to clipboard

Xinyi Mou, Chen Qian, Wei Liu, Ling Yan, Yao Hu, Xuanjing Huang, Zhongyu Wei

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated impressive ability to role-play humans and replicate complex social dynamics.
Approach:	They propose an efficient agent communication language induction for social simulations that reduces token consumption by over 20%.
Outcome:	The proposed model reduces token consumption by over 20% while preserving human language.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Agentic Verification for Ambiguous Query Disambiguation (2026.findings-acl)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Youngwon Lee, Seung-won Hwang, Ruofan Wu, Feng Yan, Danmei Xu, Moutasem Akkad, Zhewei Yao, Yuxiong He

Information Retrieval

Challenge:	Prior Diversify-then-Verify pipelines generate interpretations and then retrieve evidence . ambiguous queries require RAG to disambiguate into interpretations that can be answered from corpus .
Approach:	They propose a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early.
Outcome:	The proposed approach improves grounding-aware F1 by 23% over baselines across multiple LLMs.

DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision (2025.emnlp-industry)

Copied to clipboard

Yongqi Leng, Yikun Lei, Xikai Liu, Meizhi Zhong, Bojian Xiong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation (2021.acl-demo)

Challenge:	Recent advances in outcome-supervised reinforcement learning (RL) have shown strong performance, but this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback.
Approach:	They propose a model that models RAG as a Markov Decision Process (MDP) and introduces an efficient pruning strategy to optimize data expansion.
Outcome:	The proposed model outperforms existing methods and achieves an average performance improvement of 6.2% across six datasets.

Copied to clipboard

Weizhen Qi, Yeyun Gong, Yu Yan, Can Xu, Bolun Yao, Bartuer Zhou, Biao Cheng, Daxin Jiang, Jiusheng Chen, Ruofei Zhang, Houqiang Li, Nan Duan

From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs (2025.findings-acl)

Challenge:	Existing models for pre-training are not convenient for users to find and set them up.
Approach:	They propose to extend ProphetNet into other domains and languages by pre-training models . they pre-train a cross-lingual generation model ProphetNet-Multi and a Chinese generation model .
Outcome:	The proposed models achieve new state-of-the-art on 10 benchmarks.

Copied to clipboard

Tianle Gu, Kexin Huang, Ruilin Luo, Yuanqi Yao, Xiuying Chen, Yujiu Yang, Yan Teng, Yingchun Wang

Robustness in NLP

Challenge:	Existing approaches to unlearning often treat nonsensical responses or template-based refusals as the unlearning target, making the process even more vulnerable to attacks and jailbreaks.
Approach:	They propose a method that uses inverted facts to remove the need for auxiliary models or retaining data while avoiding leakage.
Outcome:	Evaluated on the ToFU Knowledge Unlearning dataset using Llama2-7B-Chat and Phi-1.5, MEOW outperforms baselines in forgetting quality while preserving model utility.

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)

Copied to clipboard

Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Challenge:	Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks.
Approach:	They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task.
Outcome:	The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines.

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective (2025.coling-main)

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

Copied to clipboard

Meizhi Zhong, Chen Zhang, Yikun Lei, Xikai Liu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

ASD-iLLM:An Intervention Large Language Model for Autistic Children based on Real Clinical Dialogue Intervention Dataset (2025.findings-emnlp)

Challenge:	Enabling LLMs to handle lengthy context is currently a research hotspot . a notable challenge limiting further customization is the inability of LLM to utilize context beyond pretrained length due to the inherent flaw of rotary position embedding (RoPE).
Approach:	They propose to extend the RoPE from an attention perspective and on two benchmarking tasks.
Outcome:	The proposed extension of the RoPE improves extrapolation and retrieval errors.

Copied to clipboard

Shuzhong Lai, Chenxi Li, Junhong Lai, Yucun Zhong, Chenyu Yan, Xiang Li, Haifeng Li, Gang Pan, Lin Yao, Yueming Wang

Improving Factual Consistency of News Summarization by Contrastive Preference Optimization (2024.findings-emnlp)

Challenge:	Currently, leveraging large language models (LLMs) for autism intervention is a significant yet challenging task, especially when directly employing LLMs as an intervention doctor.
Approach:	They propose a framework for training LLMs to conduct dialogue interventions in accordance with the principles of Applied Behavior Analysis (ABA) they also propose 'role-play' strategy in which LLM act as autistic children to comprehensively evaluate the doctor model's capabilities at the dialogue level.
Outcome:	The proposed framework outperforms existing models in both automatic and human evaluation, with intervention strategies and dialogue style more closely resembling those of clinical intervention doctors.

Copied to clipboard

Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma

Text Generation

Challenge:	Recent advances in news summarization have created problems with “hallucinations” that are factually inconsistent with the source text.
Approach:	They propose to disentangle LLMs’ propensities to generate faithful and fake content by adopting a probing-based specific training method to improve their capacity of distinguishing two types of propensity.
Outcome:	The proposed method disentangles LLMs’ propensities to generate faithful and fake content and improves their ability to distinguish between two types of propensity.

Persona-E²: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events (2026.acl-long)

Copied to clipboard

Yuqin Yang, Haowu Zhou, Haoran Tu, Zhiwen Hui, Shiqi Yan, HaoYang Li, Dong She, Xianrong Yao, Yang Gao, Zhanpeng Jin

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.

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)

Copied to clipboard

Zijie Dai, Shiyuan Deng, Sheng Guan, Yizhou Tian, Xin Yao, Xiao Yan, James Cheng

Unleashing the Potential of Large Language Models through Spectral Modulation (2024.findings-emnlp)

Challenge:	Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption.
Approach:	They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.
Outcome:	Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.

Copied to clipboard

Peng Sun, Yao Zhu, Yunjian Zhang, Xiu Yan, Zizhe Wang, Xiangyang Ji

Half-S: Halving the Scale for Near-Lossless 4-Bit LLM Training (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, garnering significant attention from both academia and industry.
Approach:	They propose to conduct spectral modulation in the parameter space of LLMs to integrate with various models in a plug-and-play manner.
Outcome:	The proposed approach improves performance by 10.12% with spectral modulation.

Copied to clipboard

Jinyang Du, Ruihao Gong, Linghan Ai, Zining Wang, Yunke Peng, Yao Wang, Lei Yan, null Wxuefei, Yaoyuan Wang, Jinyang Guo, Dahua Lin, Xianglong Liu

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance (2025.emnlp-main)

Challenge:	Existing 4-bit training pipelines rely on max-scaling, which causes representation collapse . despite this, there are limitations in the accuracy of 4-bit LLM training .
Approach:	They propose a scaling strategy that uses half-scaling as a hardware-friendly default . they propose fp4 support that allows for a faster scaling of large language models .
Outcome:	The proposed scaling strategy narrows the gap between theoretical optimum and BF16 while maintaining the efficiency benefits of 4-bit training.

Copied to clipboard

Sijia Yao, Pengcheng Huang, Zhenghao Liu, Yu Gu, Yukun Yan, Shi Yu, Ge Yu

Information Retrieval

Challenge:	Existing methods for enhancing dense retrieval with query augmentation ignore the alignment between generation and ranking objectives.
Approach:	They propose a unified LLM-augmented dense retrieval framework that jointly optimizes both the LLM and the retriever.
Outcome:	Experimental results show that ExpandR outperforms strong baselines, achieving more than 5% improvement in retrieval performance.

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

Creative and Context-Aware Translation of East Asian Idioms with GPT-4 (2024.findings-emnlp)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Kenan Tang, Peiyang Song, Yao Qin, Xifeng Yan

Multilinguality

Challenge:	figurative language is a challenge for human translators, who often choose a context-aware translation . a set of commonly used idioms condenses its figurativ meaning into a few characters .
Approach:	They evaluate whether GPT-4 can generate high-quality translations using Pareto-optimal prompting strategies that outperform translation engines from Google and DeepL.
Outcome:	The proposed translations outperform translation engines from Google and DeepL at low cost.

Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs (2025.findings-emnlp)

Copied to clipboard

Yao Yan

Challenge:	arithmetic offers a compact test of whether large language models compute or memorize.
Approach:	They study multi-digit addition in LLaMA-3-8B-Instruct using linear probes and the Logit Lens . they find a consistent four-stage, layer-wise ordering of probe-decodable signal types across depth .
Outcome:	The proposed method shows that multi-digit addition is linearly decodable with high accuracy across layers.

Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing (2023.acl-long)

Copied to clipboard

Hao Yan, Saurabh Srivastava, Yintao Tai, Sida I. Wang, Wen-tau Yih, Ziyu Yao

Semantic Parsing

Challenge:	Existing work on interactive semantic parsing relies on human annotations to train a model . prior work relied on human-annotated feedback data, which is prohibitively expensive and not scalable .
Approach:	They propose a task of simulating NL feedback for interactive semantic parsing . they propose evaluators to assess the quality of the simulated feedback .
Outcome:	The proposed simulator can generate high-quality NL feedback to boost the error correction ability of a specific parser.

ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)

Copied to clipboard

Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

Semantic Text Processing

Challenge:	Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases.
Approach:	They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage.
Outcome:	The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance.

Self-supervised Product Title Rewrite for Product Listing Ads (2022.naacl-industry)

Copied to clipboard

Xue Zhao, Dayiheng Liu, Junwei Ding, Liang Yao, Mahone Yan, Huibo Wang, Wenqing Yao

Responsible & Trustworthy NLP

Challenge:	Existing work has investigated the title optimization for Product Listing Ads (PLAs) however, little work has examined the effectiveness of this method.
Approach:	They propose a method to rewrite product listing ads titles without considering the fluency and information priority.
Outcome:	The proposed solution reduces the cost and improves CTR in the offline test and real-world online test by a large amount.

CodeM: Less Data Yields More Versatility via Ability Matrix (2024.findings-acl)

Copied to clipboard

Daoguang Zan, Ailun Yu, Wei Liu, Bo Shen, Shaoxin Lin, Yongshun Gong, Yafen Yao, Yan Liu, Bei Guan, Weihua Luo, Yongji Wang, Qianxiang Wang, Lizhen Cui

Challenge:	Recent efforts to train code large language models have been booming recently . however, this will incur significant costs in constructing data and training model considering the countless downstream scenarios.
Approach:	They propose a data construction strategy which decouples code LLMs’ abilities into two dimensions and constructs a lightweight training corpus that only covers a subset of target scenarios.
Outcome:	The proposed model can train a multilingual multitasking model using less data and training data.

NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries (2024.findings-eacl)

Copied to clipboard

Wei Zhao, Zhitao Hou, Siyuan Wu, Yan Gao, Haoyu Dong, Yao Wan, Hongyu Zhang, Yulei Sui, Haidong Zhang