Papers by Tong Lin

Bag of Tricks for Optimizing Transformer Efficiency (2021.findings-emnlp)

Challenge:	Knowledge distillation is an effective method for model acceleration and compression.
Approach:	They propose to use parameters to distill knowledge from large neural networks to small ones . they propose to do this by using a parameter generator to transfer the knowledge to a small neural network .
Outcome:	The proposed method learns a small network 1.88 2.94x faster than the large network but with competitive BLEU points.

Copied to clipboard

Ye Lin, Yanyang Li, Tong Xiao, Jingbo Zhu

Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization (2023.findings-emnlp)

Challenge:	Improving Transformer efficiency has become increasingly attractive in recent years.
Approach:	They propose to combine pruning, quantization, new architectures and training strategies to improve Transformer efficiency.
Outcome:	The proposed methods improve the inference efficiency of a strong Transformer system by 3.80x on CPU and 2.52x on GPU.

Copied to clipboard

Shoujie Tong, Heming Xia, Damai Dai, Runxin Xu, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui

The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations (2025.emnlp-main)

Challenge:	Pretrained language models can be fine-tuned on limited training data, which can overfit and thus diminish performance.
Approach:	They propose a fine-tuning strategy that selectively updates model parameters using gradients from various sub-nets dynamically generated by dropout.
Outcome:	The proposed method outperforms existing methods on the GLUE benchmark and exhibits excellent generalization ability and robustness for domain transfer, data imbalance, and low-resource scenarios.

Copied to clipboard

Yubo Zhu, Dongrui Liu, Zecheng Lin, Wei Tong, Sheng Zhong, Jing Shao

Disentangle to Decay: Linear Attention with Trainable Decay Factor (2025.coling-main)

Challenge:	Existing methods for difficulty estimation rely on repeated response sampling, auxiliary models, or fine-tuning the target model itself.
Approach:	They propose a method that leverages only the hidden representations produced by large language models.
Outcome:	The proposed method outperforms baselines in difficulty estimation on textual and multimodal tasks and improves adaptive reasoning strategies with fewer generated tokens.

Copied to clipboard

Haibo Tong, Chenyang Zhang, Jiayi Lin, Bingxuan Hou, Qingqing Hong, Junli Wang

LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding (2025.findings-acl)

Challenge:	Existing linear attention models use a decay factor based positional encoding (PE), but the decay factor is manually designed and non-trainable, limiting further optimization.
Approach:	They propose a PE-based positional encoding that disentangles decay factor into two parts to achieve further optimization and stable training.
Outcome:	The proposed model achieves stable training of decay factor and improves inference efficiency in normal context and extrapolation scenarios.

Copied to clipboard

Junlong Tong, Jinlan Fu, Zixuan Lin, Yingqi Fan, Anhao Zhao, Hui Su, Xiaoyu Shen

Challenge:	Existing methods for adapting LLMs to streaming rely on expensive re-encoding or limited scalability.
Approach:	They propose a group position encoding paradigm built on batch architectures to enhance consistency between streaming and batch modes.
Outcome:	The proposed method outperforms existing methods on cross-lingual and cross-modal tasks.

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction (2020.coling-main)

Copied to clipboard

Yanyang Li, Yingfeng Luo, Ye Lin, Quan Du, Huizhen Wang, Shujian Huang, Tong Xiao, Jingbo Zhu

Responsible & Trustworthy NLP

Challenge:	Recent work has questioned the robustness of unsupervised bilingual dictionary induction methods on distant language pairs.
Approach:	They propose an iterative dimension reduction method to bridge this gap . they propose a method that initializes and self-learning and inducing a dictionary .
Outcome:	The proposed method achieves 13.64 55.53% accuracy between English and four distant languages.

A Survey on LLM-based Conversational User Simulation (2026.eacl-long)

Copied to clipboard

Bo Ni, Yu Wang, Leyao Wang, Branislav Kveton, Franck Dernoncourt, Yu Xia, Hongjie Chen, Reuben Luera, Samyadeep Basu, Subhojyoti Mukherjee, Puneet Mathur, Nesreen K. Ahmed, Junda Wu, Li Li, Huixin Zhang, Ruiyi Zhang, Tong Yu, Sungchul Kim, Jiuxiang Gu, Zhengzhong Tu, Alexa Siu, Zichao Wang, Seunghyun Yoon, Nedim Lipka, Namyong Park, Zihao Lin, Trung Bui, Yue Zhao, Tyler Derr, Ryan A. Rossi

Dialogue Systems & Conversational Agents

Challenge:	Recent advances in large language models (LLMs) have enabled high-fidelity generation of synthetic user conversation.
Approach:	They propose a taxonomy covering user granularity and simulation objectives . they analyze core techniques and evaluation methodologies to help them understand the latest developments .
Outcome:	The proposed model enables high-fidelity generation of synthetic user conversation.

FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point (2025.findings-acl)

Copied to clipboard

Ke Yi, Jianwei Zhang, Zhiying Xu, Xinlong Yang, Yang Zhou, Minmin Sun, Zengke Liu, Tong Zhang, Junyang Lin, Jingren Zhou

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs (2024.emnlp-main)

Challenge:	Auto-regressive decoding is a memory-bound job, meaning decoding performance is limited by the bandwidth rather than the computational capabilities of the GPU.
Approach:	They propose a framework that supports lossless weight-only quantization inference and validate it on Qwen and LLaMA Models.
Outcome:	The proposed framework achieves the highest efficiency with lossless accuracy on Qwen and LLaMA Models across various modalities.

Copied to clipboard

Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang

Multi-Path Transformer is Better: A Case Study on Neural Machine Translation (2022.findings-emnlp)

Challenge:	Existing multi-modal large language models (MLLMs) are able to process visual inputs by converting them into visual tokens that share the same latent space as language tokens in LLMs.
Approach:	They propose a benchmark that assesses the visual illusion level given spurious images and a pipeline that converts visual inputs into visual tokens.
Outcome:	The proposed benchmark shows that MLLMs suffer from an instinctive bias to varying degrees when presented with spurious images.

Copied to clipboard

Ye Lin, Shuhan Zhou, Yanyang Li, Anxiang Ma, Tong Xiao, Jingbo Zhu

CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models (2026.acl-long)

Challenge:	Extensive experiments on 12 WMT tasks show that shallower multi-path models can achieve similar or even better performance than the deeper model.
Approach:	They propose to use a parameter-efficient multi-path structure to fuse features extracted from different paths to achieve better performance.
Outcome:	The proposed model can achieve better performance with the same number of parameters than the deeper model.

Copied to clipboard

Haibo Tong, Zeyang Yue, Feifei Zhao, Erliang Lin, Lu Jia, Ruolin Chen, Yinqian Sun, Qian Zhang, Yi Zeng

Linguistics & Cognitive NLP

Challenge:	Existing benchmarks for Large Language Models (LLMs) are limited to false belief tasks, highlighting bottlenecks in specific dimensions.
Approach:	They propose a benchmark to evaluate Large Language Models' Theory of Mind capabilities . they evaluate 8000 bilingual instances across 46 paradigms and validated by 49 human annotators .
Outcome:	The proposed benchmark reveals performance heterogeneities and bottlenecks in 22 representative models.

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models (2026.findings-acl)

Copied to clipboard

Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Challenge:	Vision-Language Models (VLMs) have advanced multimodal learning, driving progress in cross-modal reasoning.
Approach:	They propose to examine moral robustness of vision-language models by analyzing their moral stances under multimodal perturbations.
Outcome:	The proposed model-agnostic multimodal perturbations expose VLMs to a variety of moral vulnerabilities, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion.

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

PToco: Prefix-based Token-level Collaboration Enhances Reasoning for Multi-LLMs (2025.coling-main)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Yuang Bian, Yupian Lin, Jingping Liu, Tong Ruan

An Empirical Study of Instruction-tuning Large Language Models in Chinese (2023.findings-emnlp)

Challenge:	Existing approaches to collaboration between multiple Large Language Models (LLMs) rely on highly capable models with strong self-reflection abilities or are limited to models sharing the same tokenizer.
Approach:	They propose a mechanism that enables collaboration among less capable LLMs independent of tokenizer differences.
Outcome:	The proposed mechanism improves performance over individual models and generalizes well across different quantities and sizes of participating models.

Copied to clipboard

Qingyi Si, Tong Wang, Zheng Lin, Xu Zhang, Yanan Cao, Weiping Wang

FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems (2026.findings-acl)

Challenge:	emergence of ChatGPT validates the potential of large language models (LLMs) in artificial general intelligence (AGI) however, the closed source of LLMs coupled with the requirement for massive computing resources has deterred researchers from reaching the LLM training stage.
Approach:	They propose to use Chinese instruction-tuning LLMs as a cookbook for customizing LLM models that can better respond to Chinese instructions.
Outcome:	The proposed LLM can be used to customize Chinese LLMs that can better respond to Chinese instructions.

Copied to clipboard

WenHao Wang, Haoting Shi, Mengying Yuan, Yiquan Lin, Panrong Tong, Hanzhang Zhou, Guangyi Liu, Pengxiang Zhao, Yue Wang, Siheng Chen

Responsible & Trustworthy NLP

Challenge:	a lack of benchmarks capture real-world, cross-platform heterogeneity in GUI training . traditional methods to train GUI agents rely on centralized data collection and manual labeling .
Approach:	They propose a benchmark for developing and evaluating federated GUI agents across mobile, web and desktop platforms.
Outcome:	The proposed benchmarks show that cross-platform collaboration improves performance and identify platform and OS as the most influential factors.

Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding (2024.findings-emnlp)

Copied to clipboard

Derong Xu, Ziheng Zhang, Zhihong Zhu, Zhenxi Lin, Qidong Liu, Xian Wu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, Enhong Chen

Information Extraction & Text Mining

Challenge:	Medical Information Extraction (MIE) tasks are a fundamental component of medical NLP.
Approach:	They propose an alternative adaptive constraint strategy to adjust the scale and scope of contrastive tokens.
Outcome:	The proposed approach selectively enhances the identification and classification capabilities while minimizing the influence of other inherent abilities in LLMs.

VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit (2026.acl-long)

Copied to clipboard

Junda Lin, Zhaomeng Zhou, Zhi Zheng, Shuochen Liu, Tong Xu, Yong Chen, Enhong Chen

Robustness in NLP

Challenge:	Existing defenses for indirect prompt injection are limited by static protection mechanisms . existing models prioritize injected rules due to strict alignment, whereas static protections sever the feedback loop required for adaptive reasoning.
Approach:	They propose a framework that shifts the paradigm from restrictive isolation to a verify-before-commit protocol.
Outcome:	The proposed framework outperforms state-of-the-art dynamic defenses by reducing the attack success rate by over 22% while more thandoubling utility under attack compared to static baselines.

Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases (2021.acl-long)

Copied to clipboard

Boxi Cao, Hongyu Lin, Xianpei Han, Le Sun, Lingyong Yan, Meng Liao, Tong Xue, Jin Xu

DoTAT: A Domain-oriented Text Annotation Tool (2022.acl-demo)

Challenge:	Recent studies show that pre-trained masked language models can be factual knowledge bases.
Approach:	They conduct a rigorous study to explore the underlying predicting mechanisms of MLMs . they find that previous decent performance mainly owes to the biased prompts which overfit dataset artifacts a .
Outcome:	The proposed model improves on illustrative cases and external contexts . the results question the previous findings that MLMs can be reliable factual knowledge bases .

Copied to clipboard

Yupian Lin, Tong Ruan, Ming Liang, Tingting Cai, Wen Du, Yi Wang

Challenge:	DoTAT is a domain-oriented text annotation tool that can reduce the time for event annotation by 19.7% . the tool supports multi-person collaborative process with automatically merging and review .
Approach:	They propose a domain-oriented text annotation tool called DoTAT . it provides multi-person collaborative process with automatic merging and review .
Outcome:	The proposed tool can reduce the time for event annotation by 19.7% compared with existing tools.

MobileNMT: Enabling Translation in 15MB and 30ms (2023.acl-industry)

Copied to clipboard

Ye Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, Jingbo Zhu

Multilinguality

Challenge:	Existing work on NMT models is limited in storage, memory, computation and power consumption.
Approach:	They propose a mobile machine translation system that can translate in 15MB and 30ms on devices.
Outcome:	The proposed system can translate in 15MB and 30ms on mobile devices.

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)

Copied to clipboard

Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Tong Xiao

Challenge:	Existing approaches to generate relevance judgments are limited due to dynamic nature of query distributions.
Approach:	They propose a self-evolving relevance model approach to generalize queries to practical search scenarios . they use a multi-agent sample miner and a relevance annotator to generate reliable labels .
Outcome:	The proposed approach can achieve significant performance gains on a large-scale industrial platform, validated by offline multilingual evaluations and online testing.

Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)

Copied to clipboard

Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong

Robustness in NLP

Challenge:	Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise.
Approach:	They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble.
Outcome:	The proposed technique improves ensemble performance and robustness against erroneous signals.

Active Prompting with Chain-of-Thought for Large Language Models (2024.acl-long)

Copied to clipboard

Shizhe Diao, Pengcheng Wang, Yong Lin, Rui Pan, Xiang Liu, Tong Zhang

Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (2026.acl-long)

Challenge:	Existing methods to annotate large language models rely on a fixed set of human-annotated exemplars, which are not always the most effective for different tasks.
Approach:	They propose a method to adapt large language models to different tasks with task-specific example prompts (annotated with human-designed CoT reasoning) they introduce several metrics to characterize uncertainty so as to select the most uncertain questions for annotation.
Outcome:	The proposed method significantly improves performance on eight complex reasoning tasks.

Copied to clipboard

Yuanchen Bei, Tianxin Wei, Xuying Ning, Yanjun Zhao, Zhining Liu, Xiao Lin, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong

Natural Language Interfaces

Challenge:	Existing benchmarks evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts.
Approach:	They propose a benchmark for evaluating multimodal long-term conversational memory in MLLM agents.
Outcome:	The proposed framework assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management.

CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation (2025.findings-acl)

Copied to clipboard

Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (2026.acl-industry)

Challenge:	Medical quality control indicators are essential to assess the qualifications of healthcare institutions for medical services.
Approach:	They propose a Chinese electronic medical records-based dataset for MQCIC and propose CF-IR method that disentangles clinical fact verification and inferential rule reasoning actions.
Outcome:	The proposed method outperforms Chain-of-Thought methods on 20 representative LLMs, covering general and medical models.

Copied to clipboard

Guangxiang Zhao, Qilong Shi, Xusen Xiao, Xiangzheng Zhang, Tong Yang, Lin Sun

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following (2026.acl-long)

Challenge:	Reasoning LLMs often spend tokens on long intermediate reasoning traces when solving new problems.
Approach:	They propose to store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration and retrieve these skills at inference time to guide future reasoning.
Outcome:	The proposed approach reduces reasoning tokens while improving overall performance on coding and mathematical reasoning tasks.

Copied to clipboard

Yuancheng Yang, Lin Yang, Xu Wang, Chao Tong, Haihua Yang

UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression (2022.emnlp-main)

Challenge:	Experiments show that enhancing implicit reasoning capabilities can significantly improve complex instruction following in large language models.
Approach:	They propose a method to enhance LLMs’ understanding of implicit reasoning instructions by formalizing such instructions as verifiable reasoning graphs and fine-tuning with graph reasoning.
Outcome:	The proposed method outperforms existing models on five complex instruction following benchmarks and will be open-sourced in the near future.

Copied to clipboard

Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)

Challenge:	Existing work on geometry problem solving treats calculation and proving as two specific tasks hindering a deep model to unify reasoning ability on multiple math tasks.
Approach:	They propose a large-scale Unified Geometry problem benchmark to unify geometry on multiple math tasks.
Outcome:	The proposed framework outperforms the existing model with 5.6% and 3.2% accuracies on calculation and proving problems.

Copied to clipboard

Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences.
Approach:	They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles.
Outcome:	The proposed method improves performance across reward objectives and targets.

R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ (2024.naacl-long)

Copied to clipboard

Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)

Challenge:	Existing methods for instruction tuning force the model to complete a sentence no matter whether it knows the knowledge or not.
Approach:	They propose a new approach to tuning large language models to refrain from answering questions beyond its parametric knowledge by identifying the disparity in parametric and parametric information.
Outcome:	The proposed approach improves a model’s ability to answer known questions and refrain from answering unknown questions.

Copied to clipboard

Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun

Robustness in NLP

Challenge:	Existing approaches to safety alignment of large language models rely on costly manual annotations or human review.
Approach:	They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation.
Outcome:	The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability.

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues (2022.acl-long)

Copied to clipboard

Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, Zhifang Sui

Breakthrough from Nuance and Inconsistency: Enhancing Multimodal Sarcasm Detection with Context-Aware Self-Attention Fusion and Word Weight Calculation. (2024.lrec-main)

Challenge:	Existing work in vision language cross-modal reasoning uses binary or multi-choice classification based on source image and textual query.
Approach:	They propose a task where a textual premise is the background presumption on each source image.
Outcome:	The proposed task is based on a dataset of 15,360 movie screenshots and human-curated premise templates from 6 pre-defined categories.

Copied to clipboard

Hongfei Xue, Linyan Xu, Yu Tong, Rui Li, Jiali Lin, Dazhi Jiang

Sentiment Analysis

Challenge:	Existing methods for sarcasm detection rely on feature concatenation to fuse different modalities or model inconsistencies among modalités.
Approach:	They propose to use Context-Aware Self-Attention Fusion to integrate local and momentary multimodal information into specific words to illustrate the inconsistencies between connotation and denotation.
Outcome:	The proposed method achieves an accuracy of 76.9 and an F1 score of 76.1 on the MUStARD dataset, surpassing the current state-of-the-art IWAN model by 1.7 and 1.6 respectively.

Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method (2024.findings-emnlp)

Copied to clipboard

Jiayi Lin, Chenyang Zhang, Haibo Tong, Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Junli Wang

Information Retrieval

Challenge:	Prior work focuses on designing specific methods or applying heuristic strategies to encourage models to predict more correct predictions.
Approach:	They propose a framework that uses a post-processing strategy to handle incorrect predictions.
Outcome:	The proposed framework significantly improves the Exact Match scores on multiple MSQA datasets.

ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation (2023.findings-emnlp)

Copied to clipboard

Zi Lin, Zihan Wang, Yongqi Tong, Yangkun Wang, Yuxin Guo, Yujia Wang, Jingbo Shang

Dialogue Systems & Conversational Agents

Challenge:	toxicity detection has been largely based on social media content, leaving the unique challenges inherent to real-world user-AI interactions insufficiently explored.
Approach:	They propose a benchmark to detect toxicity in real-world user-AI conversations . they compare existing models with social media content to find toxicity .
Outcome:	The proposed benchmark reveals that existing models fail to recognize toxicity in real-world user-AI conversations.

Text-to-ES Bench: A Comprehensive Benchmark for Converting Natural Language to Elasticsearch Query (2025.acl-long)

Copied to clipboard

DonggeXue DonggeXue, Zhili Pu, Zhentao Xia, Hongli Sun, Ruihui Hou, Guangya Yu, Yupian Lin, Yongqi Fan, Jingping Liu, Tong Ruan

Information Retrieval

Challenge:	Recent research on text-to-Query has explored using large language models to convert user query intent to executable code.
Approach:	They propose a novel semantic parsing task that leverages large language models to generate domain-specific language and post-processing code to support multi-index Elasticsearch queries.
Outcome:	The proposed model outperforms DeepSeek-R1 on the large Elasticsearch Dataset (LED) and BirdES datasets.

VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization (2026.acl-long)

Copied to clipboard

Dingyu Yao, Chenxu Yang, Zhengyang Tong, Zheng Lin, Wei Liu, Jian Luan, Weiping Wang

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs (2026.acl-long)

Challenge:	Existing quantization methods for large language models suffer performance degradation at ultra-low bit-widths due to key cache outliers.
Approach:	They propose a vector quantization method that suppresses outliers in the key cache and reduces memory access overhead.
Outcome:	The proposed method outperforms baseline quantization methods across long-context understanding and mathematical reasoning tasks while minimizing memory access overhead.

Copied to clipboard

Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, MuRun Yang, DingYang Lin, Kaiyan Chang, Tong Zheng, Bei Li, Peinan Feng, Quan Du, Tong Xiao, JingBo Zhu

Multilinguality

Challenge:	Large language models have significantly advanced Multilingual Machine Translation (MMT) yet scaling to many languages while maintaining robust performance across directions remains challenging.
Approach:	They propose a strategy to reduce the number of translations in one direction . they propose auxiliary parallel sentences to promote cross-lingual transfer .
Outcome:	The proposed model performs on par with or better than substantially larger baselines.

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization (2024.findings-emnlp)

Copied to clipboard

Yong Lin, Skyler Seto, Maartje Ter Hoeve, Katherine Metcalf, Barry-John Theobald, Xuan Wang, Yizhe Zhang, Chen Huang, Tong Zhang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences.
Approach:	They compare the accuracy of DPORM and EXRM with a reward function for scoring human preferences.
Outcome:	The proposed methods can approximate an EXRM on the limit infinite samples, but it is unclear how effective they are in practice.

Enrich, Aggregate, and Generate: Three-stage Biomedical Data-to-Text Generation Using Large Language Models in Low-resource Scenarios (2026.findings-acl)

Copied to clipboard

Yupian Lin, Guangya Yu, Yuang Bian, Cheng Yuan, Hui Luo, Tong Ruan

Text Generation

Challenge:	Biomedical data-to-text generation is a branch of Natural Language Generation, aiming at generating textual natural language descriptions that can fluently and precisely describe the structured data.
Approach:	They propose an LLM framework that can be used to generate textual natural language descriptions using in-context learning.
Outcome:	The proposed framework provides good interpretability and superior performance on the BioLeaflets dataset.

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment (2026.acl-industry)

Copied to clipboard

Yingfeng Luo, Hongyu Liu, DingYang Lin, Kaiyan Chang, Chenglong Wang, Bei Li, Quan Du, Tong Xiao, JingBo Zhu

Machine Translation

Challenge:	Existing routing strategies rely on heuristics, external predictors, or absolute quality estimation to capture whether the large model provides a worthwhile improvement over the small one.
Approach:	They propose a budget allocation problem for routing large model to large model . they propose heuristics, external predictors, or absolute quality estimation to determine the optimal signal for budgeted decisions.
Outcome:	The proposed model outperforms heuristics, quality/difficulty estimation baselines and achieves a superior quality–budget Pareto frontier.

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing (2026.acl-long)

Copied to clipboard

Tong Zhang, Honglin Lin, Zhou Liu, Chong Chen, Wentao Zhang

Tab2Text - A framework for deep learning with tabular data (2024.findings-emnlp)

Challenge:	Existing benchmarks for scientific diagram generation rely on image-centric metrics or evaluation of intermediate symbolic representations rather than final rendered images.
Approach:	They propose a structure-first benchmark for evaluating scientific diagram generation from pixel-level outputs.
Outcome:	The proposed benchmark evaluates scientific diagram generation directly from pixel-level outputs.

Copied to clipboard

Tong Lin, Jason Yan, David Jurgens, Sabina Tomkins

LogToP: Logic Tree-of-Program with Table Instruction-tuned LLMs for Controlled Logical Table-to-Text Generation (2026.findings-eacl)

Challenge:	Tabular data is a foundational part of social sciences and is used to fit supervised learning models.
Approach:	They propose a technique for transforming tabular data to text data to improve deep learning models for tabular datasets.
Outcome:	The proposed technique improves performance of deep learning models for tabular data.

Copied to clipboard

Yupian Lin, Guangya Yu, Cheng Yuan, Huan Du, Hui Luo, Yuang Bian, Jingping Liu, Zhidong He, Wen Du, Tong Ruan

Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation (2026.findings-acl)

Challenge:	Existing LLMs are difficult to achieve satisfactory results in table-related tasks.
Approach:	They propose to develop a specialized logical table-to-text generation model that can be used for table-related tasks.
Outcome:	The proposed model achieves state-of-the-art on a Logic2Text dataset.

Copied to clipboard

Jinwen Chen, Hainan Zhang, Liang Pang, Yongxin Tong, Haibo Zhou, Wei Lin, Zhiming Zheng

Responsible & Trustworthy NLP

Challenge:	Existing RAG systems require uploading local documents to the cloud, resulting in inference latency and poor generalization on out-of-distribution (OOD) inputs.
Approach:	They propose a generalizable knowledge-distilled parametric RAG model aligned with standard RAG in document structure and parameter activation.
Outcome:	The proposed model outperforms baselines in accuracy and generalizes well on out-of-distribution (OOD) data.

Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models (2024.lrec-main)

Copied to clipboard

Derong Xu, Ziheng Zhang, Zhenxi Lin, Xian Wu, Zhihong Zhu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, Enhong Chen