Papers by Deyi Xiong
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)
Copied to clipboard
Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong
| 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. |
MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing systems rely heavily on literature retrieval and synthesis, resulting research lacking insight and creativity in social science. |
| Approach: | They propose a method that leverages highly realistic social simulations to the creativity of LLMs-generated research. |
| Outcome: | The proposed model shows a 6.81% improvement in quality over foundation LLMs and 17.19% gain in Insight over strong baselines. |
CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing speech-to-text translation models can extract features from speech inputs, but they may include non-linguistic speech factors such as pitch, timbre and speaker identity. |
| Approach: | They propose a content-centric speech representation disentanglement learning framework for speech translation that decomposes speech representations into content representations and non-linguistic representations via representation disentanglement learning. |
| Outcome: | The proposed framework outperforms state-of-the-art speech translation models and cascaded models on five translation directions. |
Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons (2025.coling-main)
Copied to clipboard
| Challenge: | Despite their superior multitask capabilities, the multitask learning mechanisms of large language models remain as an open question. |
| Approach: | They propose a method that fine-tunes current task-specific neurons during continuous learning by using gradient attribution on task-specified data. |
| Outcome: | The proposed method is highly correlated with the given task and solves two common problems in multi-task learning and continuous learning: Generalization and Catastrophic Forgetting. |
Automated Progressive Red Teaming (2025.coling-main)
Copied to clipboard
| Challenge: | Automated red teaming (ART) is effective but time-consuming, costly and lacks scalability. |
| Approach: | They propose an automated red teaming framework that generates adversarial prompts to expose LLM vulnerabilities. |
| Outcome: | The proposed framework explores and exploits LLM vulnerabilities through multi-round interactions. |
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech translation models learn acoustic representations from the encoder, which is not desirable for cross-modal and cross-lingual translation. |
| Approach: | They propose an adaptive speech-to-text translation model that dynamically adapts acoustic states in the decoder. |
| Outcome: | The proposed model outperforms state-of-the-art speech translation models on two widely-used datasets. |
CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies integrate word embeddings with cognitive features into neural models of natural language processing (NLP) but there are some issues in the use of cognitive features in NLP. |
| Approach: | They propose a cog-align approach that aligns textual and cognitive inputs to capture differences and commonalities. |
| Outcome: | The proposed model improves on three NLP tasks with multiple cognitive features over state-of-the-art models. |
ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models (2026.findings-acl)
Copied to clipboard
Zhen Wang, Yuqi Ren, Yuehan Cui, Hongxiang Wang, Jianxiang Peng, Zhaoxia Zhang, Bingkun Zhu, Tongxuan Zhang, Dezhi Tong, Deyi Xiong
| Challenge: | Existing methods for social simulations mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems. |
| Approach: | They propose a framework employing 14 Sociological Expert Agents to interpret World Values Survey responses through structured professional perspectives rather than direct responses concatenation. |
| Outcome: | Experiments on 480 individuals from 12 countries show that ExpertIVS outperforms baselines in value generalization and significantly outperfies the existing methods. |
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings (P18-1)
Copied to clipboard
| Challenge: | Neural machine translation uses source and target word embeddings to improve translation quality . source and targeted word embeds are at the two ends of a long information processing procedure . |
| Approach: | They propose a method to shorten the distance between source and target words in neural machine translation by bridging source and targeting word embeddings. |
| Outcome: | The proposed method shortens the distance between source and target words in neural machine translation and strengthens their association. |
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models (2026.acl-long)
Copied to clipboard
Ling Shi, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Yangyang Liu, Linlong Xu, Longyue Wang, Deyi Xiong, Weihua Luo
| Challenge: | Recent research in mechanistic interpretability has revealed that Large Language models contain disentangled, human-understandable components. |
| Approach: | They propose a framework that first identifies causal task features through frequency recall and interventional filtering, then selects “Feature-Resonant Data” that maximally activates task features for fine-tuning. |
| Outcome: | The proposed framework outperforms existing models on mathematical reasoning, summarization, and translation tasks while using only 50% of the data. |
Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. |
| Approach: | They extend previous research that shows certain abstract concepts are linearly represented as directions in LLMs, predominantly centered around English. |
| Outcome: | The proposed model can be used to align LLMs with human values, and it can generate toxic, untruthful, biased, and even illegal content. |
Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context. |
| Approach: | They propose a hierarchical model to learn document context for document-level neural machine translation . they use a sentence encoder to capture intra-sentence dependencies and a document encoder . |
| Outcome: | The proposed model significantly improves document-level translation performance over strong baselines. |
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter (2021.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to generating NMT adversarial examples inject perturbations into source sentences or target translations to improve the robustness of NMT models. |
| Approach: | They investigate adversarial attack on NMT from two aspects: languages (the source vs. the target language) and positions (front v. rear). |
| Outcome: | The proposed approach is more effective than adversarial attacks by sampling positions randomly or according to gradients. |
CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models (2024.findings-acl)
Copied to clipboard
Linhao Yu, Yongqi Leng, Yufei Huang, Shang Wu, Haixin Liu, Xinmeng Ji, Jiahui Zhao, Jinwang Song, Tingting Cui, Xiaoqing Cheng, Liutao Liutao, Deyi Xiong
| Challenge: | Recent years have witnessed remarkable progress achieved by large language models in both natural language understanding and generation. |
| Approach: | They propose a large benchmark CMoralEval for moral evaluation of Chinese LLMs . they use a Chinese TV program discussing Chinese moral norms and Chinese moral anomies based on various sources . |
| Outcome: | The proposed dataset is characterized by diversity and authenticity. |
Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in Math (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing data annotation methods suffer from high annotation cost and lack of effective automatic validation. |
| Approach: | They propose a Fine-grained Multi-Agent Debate framework and a dataset that prompts multiple agents to debate and then a Multi-agent Debates Reward Model (MRM) to improve its mathematical reasoning capabilities. |
| Outcome: | The proposed model outperforms the state-of-the-art methods by 1.2% and 3.5% on a GSM8K dataset and 45.1% on the MATH dataset. |
Towards Robust In-Context Learning for Machine Translation with Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Experimental results demonstrate the effectiveness of our method, particularly in domain adaptation. |
| Approach: | They propose a method to retrieve translation pairs as demonstrations from an additional datastore to guide translation without updating the LLMs. |
| Outcome: | The proposed method reduces noise and improves translation performance in domain adaptation. |
ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing efforts to improve reasoning efficiency of large language models focus on modifying the reinforcement learning reward, such as adding length penalties. |
| Approach: | They propose a training framework that elicits efficient reasoning through reasoning vectors and a framework that allows the model to generate high-quality responses during reinforcement learning. |
| Outcome: | The proposed framework reduces reasoning length by 30% while maintaining stability, while retaining high accuracy. |
Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations of Large Language Models (LLMs) focus on item-level behavioral metrics without capturing how models prioritize competing values as a whole. |
| Approach: | They propose a symmetric human-LLM evaluation framework to measure value-structure alignment . they evaluate 12 LLMs across four model families via 240 replicated Q-sorts . |
| Outcome: | The proposed framework measures value-structure alignment across four model families. |
Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing conversational question answering datasets are usually constructed from unstructured texts in English. |
| Approach: | They propose a Chinese tabular conversational question answering dataset based on financial reports . they select 2,463 tables and manually generate 2,463, conversations with 35,494 QA pairs . |
| Outcome: | The proposed dataset is based on Chinese financial reports extracted from listed companies in the past 30 years. |
OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety (2024.acl-demos)
Copied to clipboard
Chuang Liu, Linhao Yu, Jiaxuan Li, Renren Jin, Yufei Huang, Ling Shi, Junhui Zhang, Xinmeng Ji, Tingting Cui, Liutao Liutao, Jinwang Song, Hongying Zan, Sun Li, Deyi Xiong
| Challenge: | a rapid development of Chinese large language models poses big challenges for efficient LLM evaluation. |
| Approach: | They propose an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. |
| Outcome: | The evaluation platform OpenEval benchmarks Chinese LLMs across capability, alignment and safety. |
Towards a Deep Understanding of Multilingual End-to-End Speech Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent years have witnessed the rapid development of end-to-end speech-totext translation (ST) which has demonstrated remarkable performance and outperformed conventional cascaded systems. |
| Approach: | They employ Singular Value Canonical Correlation Analysis to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. |
| Outcome: | The proposed approach outperforms existing cascaded systems in predicting phonetic features and improves translation quality. |
Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search (2025.acl-long)
Copied to clipboard
Linhao Yu, Xingguang Ji, Yahui Liu, Fanheng Kong, Chenxi Sun, Jingyuan Zhang, Hongzhi Zhang, V. W., Fuzheng Zhang, Deyi Xiong
| Challenge: | Existing benchmarks and evaluation protocols suffer from inadequate or homogeneous creation of key points, exorbitant cost of data creation, and limited evaluation scopes. |
| Approach: | They propose an automatic framework which leverages Monte Carlo Tree Search to construct numerous and diverse descriptive sentences that thoroughly represent video content in an iterative way. |
| Outcome: | The proposed framework improves MCTS-VCB and DREAM-1K on video captioning tasks by 25.0% and 16.3% respectively. |
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning (2020.coling-main)
Copied to clipboard
| Challenge: | Paraphrase generation is of great importance for many downstream tasks in natural language processing. |
| Approach: | They propose a method to generate sentences as learning objectives from the learned data distribution and employ reinforcement learning to combine these new learning objectives for model training. |
| Outcome: | The proposed method gains significant diversity and improves generation quality over state-of-the-art datasets. |
BackMATH: Towards Backward Reasoning for Solving Math Problems Step by Step (2025.coling-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive results in reasoning, but when faced with more complex mathematical problems, performance drops significantly. |
| Approach: | They propose a backward reasoning dataset that includes 14K backward thinking problems and 100K reasoning steps. |
| Outcome: | The proposed model achieves an accuracy of 68.1% on the GSM8K dataset and 21.9% on the MATH dataset, exceeding the SOTA by 1.6% and 2.1% respectively. |
Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches (C18-1)
Copied to clipboard
| Challenge: | Current neural machine translation systems translate a text sentence-by-sentence, ignoring cross-sentent links and dependencies. |
| Approach: | They propose a cache-based approach to modeling coherence for neural machine translation . they capture contextual information either from recently translated sentences or the entire document . |
| Outcome: | The proposed model improves on state-of-the-art translation models on many languages . it captures contextual information from recently translated sentences or the entire document . |
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to zero-shot transfer knowledge from rich-resource to low-resourced languages are limited due to linguistic discrepancies in different languages. |
| Approach: | They propose a multilingual MRC framework equipped with a Siamese Semantic Disentanglement Model to disassociate semantics from syntax in models learned by multilingual pre-trained models. |
| Outcome: | The proposed model disassociates semantics from syntax in multilingual models. |
CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models behave consistently with human goals, values and intentions, but are computationally expensive. |
| Approach: | They propose a framework that enables weak-to-strong alignment transfer via concept transplantation. |
| Outcome: | The proposed framework surpasses instruction-tuned models in terms of truthfulness. |
CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent Discovery (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to intent discovery cluster novel intents with prior knowledge from intent-labeled data in a semi-supervised way. |
| Approach: | They propose a semi-supervised intent discovery framework CoCoID with two components . they propose to discriminate user utterance representation learning and intra-cluster knowledge distillation . |
| Outcome: | The proposed framework outperforms state-of-the-art intent discovery models by over 1.4 ACC and ARI points and 1.1 NMI points across four datasets. |
Lipschitz Constrained Parameter Initialization for Deep Transformers (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies show that deep Transformers have difficulty in training even with residual connection and layer normalization. |
| Approach: | They propose a method that leverages the Lipschitz constraint on the initialization of Transformer parameters to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. |
| Outcome: | The proposed model outperforms previous RNN/CNN models but fails to converge with the original computation order. |
Learning Hard Retrieval Decoder Attention for Transformers (2021.findings-emnlp)
Copied to clipboard
| Challenge: | In this paper, we show that learning a hard retrieval attention that attends to a single token in a sentence is 1.43 times faster than the standard scaled dot-product attention. |
| Approach: | They propose a method to learn hard retrieval attention where an attention head attends to a single token in a sentence rather than all tokens. |
| Outcome: | The proposed method is 1.43 times faster in decoding while preserving translation quality on a wide range of MT tasks. |
APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation (2026.acl-long)
Copied to clipboard
Pengyun Zhu, Qiheng Sun, Long Wen, Yanbo Wang, Yang Cao, Junxu Liu, Deyi Xiong, Jinfei Liu, Zhibo Wang, Kui Ren
| Challenge: | a lack of high-quality English privacy policy corpus optimized for legal clarity and readability is limiting translation of privacy policies . 139 privacy policies are often considered "incomprehensible" due to technical jargon, legal language, and convoluted grammatical structures. |
| Approach: | They propose a high-quality English privacy policy corpus annotated by domain experts . they propose APPSI-139 to summarize and interpret privacy policies in English . |
| Outcome: | The proposed framework outperforms large language models in terms of readability and accuracy. |
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting. |
| Approach: | They propose a feature-level mechanistic analysis methodology to probe RL generalization using a controlled experimental setup. |
| Outcome: | The proposed method identifies a compact, task-agnostic set of features that directly mediate generalization across diverse tasks. |
A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear. |
| Approach: | They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss . |
| Outcome: | The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks. |
Learning Source Phrase Representations for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to machine translation have been shown to be effective for long sentences . however, the attentional network can't capture long-distance dependencies . |
| Approach: | They propose a multi-head attention mechanism which generates phrase representations from token representations and incorporates them into the Transformer translation model to enhance its ability to capture long-distance relationships. |
| Outcome: | The proposed model can be computed in parallel and improves on the WMT 14 tasks. |
X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents (2023.findings-acl)
Copied to clipboard
Mehrad Moradshahi, Tianhao Shen, Kalika Bali, Monojit Choudhury, Gael de Chalendar, Anmol Goel, Sungkyun Kim, Prashant Kodali, Ponnurangam Kumaraguru, Nasredine Semmar, Sina Semnani, Jiwon Seo, Vivek Seshadri, Manish Shrivastava, Michael Sun, Aditya Yadavalli, Chaobin You, Deyi Xiong, Monica Lam
| Challenge: | X-RiSAWOZ dataset has more than 18,000 human-verified dialogue utterances for each language . Xiaoping and Xinhui are the main challenges for task-oriented dialogue research . |
| Approach: | They develop a toolkit to accelerate the post-editing of a new language dataset after translation . their dataset, code, and toolkit are released open-source . |
| Outcome: | The proposed toolkit accelerates the post-editing of a new language dataset after translation. |
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling (2020.coling-main)
Copied to clipboard
| Challenge: | Existing joint models for intent detection and slot filling show insufficient robustness . however, some small changes of inputs can fool the models to produce wrong predictions . |
| Approach: | They propose a joint adversarial training model that generates adversarials to attack the joint model and trains the model to defend against the adversarial examples. |
| Outcome: | The proposed model achieves significantly higher scores and improves robustness on two datasets. |
Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs. |
| Approach: | They propose a framework with three modules designed to assess diversity, redundancy, and difficulty. |
| Outcome: | The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs. |
Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)
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
| 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. |
Shallow Discourse Annotation for Chinese TED Talks (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to annotate text with discourse properties are limited to newspaper articles and are not available in Chinese. |
| Approach: | They propose to annotate TED talks with Chinese-related properties using the Penn Discourse TreeBank annotation style . they propose to use planned monologues instead of written text to annnotate Chinese-specific properties. |
| Outcome: | The proposed method is able to achieve reliable results in Chinese spoken monologues, and is based on the Penn Discourse TreeBank annotation style. |
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong
| Challenge: | Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure. |
| Approach: | They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction. |
| Outcome: | The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models. |
GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue (D19-1)
Copied to clipboard
| Challenge: | Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. |
| Approach: | They propose a unified end-to-end Generative Ellipsis and CO-reference Resolution model . the model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user . |
| Outcome: | The proposed model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user . intrinsic evaluations on the resolution of ellipsis and co-reference show that the model outperforms the baseline model in terms of EM, BLEU and F1 . |
Accelerating Neural Transformer via an Average Attention Network (P18-1)
Copied to clipboard
| Challenge: | Using parallelizable attention networks, the neural Transformer is slow to train due to auto-regressive architecture and self-attention in the decoder. |
| Approach: | They propose an average attention network to replace the original self-attention model in the decoder of the neural Transformer. |
| Outcome: | The proposed network can decode sentences over four times faster than the original version with almost no loss in training time and translation performance. |
Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability Patching (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing gradient-based attribution methods are inapplicable to adversarial attacks . et al.: Targeted neuron tuning improves model robustness against jailbreak attacks despite the model's vulnerability to jailbreak. |
| Approach: | They propose a gradient-based method to identify key neurons sensitive to adversarial behaviors in open-ended generation tasks. |
| Outcome: | The proposed method detects key neurons sensitive to adversarial behaviors in open-ended tasks. |
Towards a Unified Paradigm of Concept Editing in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Concept editing aims to control specific concepts in large language models (LLMs) however, there is a lack of rigorous theoretical analysis and a unified perspective to systematically understand and compare these methods. |
| Approach: | They propose a paradigm where conceptual injection is aligned at the neuron level. |
| Outcome: | The proposed paradigm offers a clear framework and valuable insights for advancing interpretability and controlled generation in large language models. |
C²RBench: A Chinese Complex Reasoning Benchmark for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks often fail to capture complex multi-step reasoning demands inherent in real-world scenarios. |
| Approach: | They propose a benchmark to evaluate multi-step, multimodal advanced reasoning of large language models. |
| Outcome: | The proposed benchmark exceeds existing benchmarks in cognitive complexity and accuracy by over 90% . it features 1,115 carefully curated Chinese tasks organized into eight domain-specific subsets . evaluations of 20 LLMs and 24 multimodal large language models reveal critical performance gaps . |
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change (2020.acl-main)
Copied to clipboard
| Challenge: | Compared to previous studies, the performance of neural models is likely to be affected by the choice of hyper-parameters. |
| Approach: | They propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate. |
| Outcome: | The proposed approach improves the Transformer model with a fixed 25k batch size by +0.73 and +0.82 BLEU respectively. |
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a test suite to evaluate commonsense reasoning capability of neural machine translation is presented . language models pretrained on large-scale corpora achieve a commonsensing accuracy of lower than 72% on target translations of this test suite. |
| Approach: | They propose a test suite to evaluate the commonsense reasoning capability of neural machine translation. |
| Outcome: | The proposed test suite performs poorly on commonsense reasoning of the three ambiguity types in terms of reasoning accuracy and reasoning consistency. |
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping (2026.acl-long)
Copied to clipboard
| Challenge: | Current Large Language Models (LLMs) rely on coarse-grained national labels for pluralistic value alignment. |
| Approach: | They propose a framework for fine-grained pluralistic value alignment using demographic constraints. |
| Outcome: | The proposed framework can identify groups with predictable, high-consensus value preference . it achieves 48.6% accuracy, surpassing open-source LLM DeepSeek-v3.2 . |
Informative Language Representation Learning for Massively Multilingual Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies show that prepending language tokens fail to guide translation into right directions, especially on zero-shot translation. |
| Approach: | They propose to use language embedding embodiment and language-aware multi-head attention to learn informative language representations to channel translation into right directions. |
| Outcome: | The proposed methods improve translation direction guidance and significantly alleviate off-target translation issues on two datasets. |
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)
Copied to clipboard
Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong
| Challenge: | Existing evaluation methods are inadequate to evaluate large language models (LLMs). |
| Approach: | They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models. |
| Outcome: | The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results. |
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has attracted wide attention in recent years. |
| Approach: | They propose a probing-based approach to measure word translation accuracy using transformer layers. |
| Outcome: | The proposed model outperforms previous probing-based translation models. |
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)
Copied to clipboard
Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong
| Challenge: | Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages. |
| Approach: | They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English. |
| Outcome: | The proposed model outperforms open-source and Tibetan-focused models on diverse tasks. |
Self-Pluralising Culture Alignment for Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to align large language models don't take cultural diversity into account. |
| Approach: | They propose a framework that generates questions on various culture topics and outputs to LLMs under both culture-aware and culture-unaware settings. |
| Outcome: | The proposed framework improves the alignment of large language models to diverse cultures without compromising general abilities. |
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling (2020.emnlp-main)
Copied to clipboard
| Challenge: | RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues spanning over 12 domains . despite of substantial progress made, there are challenges in creating challenging datasets in terms of size, multiple domains, semantic annotations and complexity. |
| Approach: | They propose a large-scale multi-domain Chinese Wizard-of-Oz dataset with rich semantic annotations that captures discourse phenomena for task-oriented dialogue modeling. |
| Outcome: | The proposed dataset contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues with more than 150K utterances spanning over 12 domains. |
Evaluating and Improving Graph to Text Generation with Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have revolutionized natural language processing due to their zero-and-short-shot capabilities. |
| Approach: | They propose a tuning-free prompting approach for graph-to-text generation tasks. |
| Outcome: | The proposed approach improves LLMs on graph-to-text generation tasks incrementally. |
LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown promising results in multilingual translation with limited bilingual supervision. |
| Approach: | They propose a Language-Aware Neuron Detecting and Routing framework that fine tunes LLMs to Machine Translation with diverse translation training data. |
| Outcome: | The proposed framework selectively finetunes LLMs to MT tasks with diverse translation training data. |
ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Paraphrasing is an important data augmentation approach for natural language processing (NLP). |
| Approach: | They propose to extract sentence-level paraphrases from multiple Chinese translations and construct a larger Chinese parabank with 22M sentence pairs. |
| Outcome: | The proposed parabank is the largest to date in Chinese, but limited by one-to-many translation data. |
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training. |
| Outcome: | The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance. |
Towards Linear Time Neural Machine Translation with Capsule Networks (D19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) is an endto-end learning approach to machine translation. |
| Approach: | They propose a capsule network with dynamic routing for linear time Neural Machine Translation . they map the source sentence into a matrix with pre-determined size and apply a deep LSTM network to decode the target sequence from the source representation. |
| Outcome: | The proposed network achieves comparable results with the Transformer system on English-German and English-French tasks. |
Encoding Gated Translation Memory into Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation (MT) technology has made significant progress in the past few years. |
| Approach: | They propose a method to combine the strengths of TM and neural machine translation (NMT) they use a gating mechanism to balance the impact of the TM match on the NMT decoder . |
| Outcome: | The proposed method improves translation quality by over 10 BLEU points when fuzzy matches are higher than 50% on the UN corpus. |
EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language models (LLMs) face challenges in the design of research workflows and multi-role collaboration mechanisms. |
| Approach: | They propose a multi-agent scientific collaboration framework which integrates bio-inspired evolution with knowledge graph modeling. |
| Outcome: | EvoSci outperforms baselines in peer-review and ranking evaluations on real-world research topics. |
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
| 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. |
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing compression approaches remove entire experts, disrupting routing topology and harming performance, or rely on unstructured weight pruning with limited practical efficiency. |
| Approach: | They propose a structured **T**rapezoidal **E**xpert **N**euron **P**running framework that uses a trapezoidal pattern to identify and retain important experts while applying expert neuron pruning (ENP) to less important experts. |
| Outcome: | The proposed framework outperforms the full-parameter model by 10% on code generation tasks under a sparse activation of experts and a 40% routing sparsity. |
DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events? (2025.emnlp-main)
Copied to clipboard
| Challenge: | a new study examines the safety implications of large language models in diplomatic positions . it identifies potential risks and ideological biases that could arise from LLMs . |
| Approach: | They propose an LLM-based multi-agent system for diplomatic position analysis . they propose ethical constraint measures to enhance the safety of LLMs . |
| Outcome: | The proposed system assesses the safety implications of large language models in diplomacy . it reveals that LLMs could exhibit a strong bias towards interests, leading to unsafe decisions . |
Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing neural machine translation models are not able to translate dialogues in real life scenarios. |
| Approach: | They propose a joint learning method to identify omission and typos and utilize context to translate dialogue utterances. |
| Outcome: | The proposed method improves translation quality by 3.2 BLEU over baselines and recovers omitted pronouns by 47.16%. |
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have demonstrated that pretrained language models memorize and regurgitate a significant portion of training data, including atypical data points that appear only once in the training data. |
| Approach: | They propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model in batches. |
| Outcome: | The proposed method eliminates the impact of privacy data in the model in batches without affecting the model's performance. |
Generating Highly Relevant Questions (D19-1)
Copied to clipboard
| Challenge: | Existing neural QG models generate generic questions that are not relevant to passages and answers. |
| Approach: | They propose to prioritize words that are morphologically close to words in the passage when generating questions. |
| Outcome: | The proposed methods improve relevance of generated questions to passages and answers. |
An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent years have witnessed that massively multilingual neural machine translation (MMNMT) achieves a remarkable progress in both high- and low-resource language translation. |
| Approach: | They propose to use a robustness evaluation benchmark dataset to assess the translation robustness of Indonesian-Chinese translation in the face of various naturally occurring noise. |
| Outcome: | The proposed dataset is publicly available at https://github.com/ID-ZH-MTRobustEval. |
IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the pre-training phase of large language models, but this study focuses on the learning phase of pre-trained LLMs. |
| Approach: | They propose a 2-phase automated curriculum learning guided instruction tuning framework that learns easy-to-hard instructions in a self-adjusting dynamic manner. |
| Outcome: | The proposed framework unlocks latent ability in pre-trained large language models and achieving superior performance across diverse tasks. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
Copied to clipboard
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
| Challenge: | Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. |
| Approach: | They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations. |
| Outcome: | The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work. |
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that multilingual pretrained models can recall factual knowledge without additional fine-tuning. |
| Approach: | They propose two parameter-free language representation projection modules to transfer factual knowledge between English and non-English languages. |
| Outcome: | The proposed modules improve factual knowledge retrieval accuracy and transferability across diverse non-English languages. |
Secoco: Self-Correcting Encoding for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a challenging field due to the wide variety of noises in real-world scenarios. |
| Approach: | They propose a framework that explicitly deals with noisy inputs for robust neural machine translation by introducing self-correcting predictors. |
| Outcome: | The proposed framework can correct noisy inputs and delete specific errors with the translation decoding process. |
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on syntactically controlled paraphrase generation rely on large-scale parallel data. |
| Approach: | They propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder which can generate texts in a specified syntastic structure. |
| Outcome: | The proposed model can generate diverse paraphrases with specified syntactic structure using non-parallel data. |
Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models alleviate segmentation ambiguity and out-of-vocabulary (OOV) words. |
| Approach: | They propose a semisupervised neural method which distills knowledge from unlabeled data to a student model to improve both in-domain and out-of-domain CWS. |
| Outcome: | The proposed method can keep practicability of the lightweight student model and improve segmentation effectively on downstream Chinese NLP tasks. |
CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API Interactions (2024.findings-acl)
Copied to clipboard
| Challenge: | a benchmark is designed to evaluate the capabilities of large language models (LLMs) as agents in decision making and operational tasks. |
| Approach: | They propose a benchmark to evaluate LLMs in the context of Chinese societal applications . they propose he benchmark will evaluate tool invocation ability of LLM and task completion ability . |
| Outcome: | The proposed benchmark features 398 APIs across 27 widely-used Apps across 14 domains. |
Efficient Cluster-Based k-Nearest-Neighbor Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | k-Nearest-Neighbor Machine Translation (kNN-MT) is a non-parametric solution for domain adaptation . previous studies have shown that kNN retrieval is at the expense of high latency . |
| Approach: | They propose to use clustering to improve retrieval efficiency by combining a non-parametric MT with an in-domain feature-based retrieval module. |
| Outcome: | The proposed method reduces translation latency by 57% while maintaining the most useful information of the original datastore. |
CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | a dataset of Chinese large language models is used to measure societal biases . many studies have shown that LLMs exhibit harmful societal biased outputs despite human data . |
| Approach: | They present a Chinese Bias Benchmark dataset that includes over 100K questions constructed by human experts and generative language models. |
| Outcome: | The proposed dataset covers stereotypes and societal biases in 14 social dimensions related to Chinese culture and values. |
DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for large language models with context length limitations are suboptimal for initialization and fine-tuning. |
| Approach: | They propose a RoPE-based fine-tuning framework that strategically determines the best scaling factors for LLMs by a Divide-and-Conquer Incremental Search algorithm. |
| Outcome: | The proposed framework mitigates performance decay at extended target lengths and can perform effectively without fine-tuning. |
Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks (D18-1)
Copied to clipboard
| Challenge: | Existing gated recurrent networks have a vanishing gradient, allowing for more matrix transformations and less transparent functions. |
| Approach: | They propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. |
| Outcome: | The proposed system is more transparent than LSTM/GRU due to the simplification. |
AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing solutions, such as memory-based agents, rely on explicit context concatenation, which leads to context dilution, high inference latency, and superficial knowledge integration. |
| Approach: | They propose an adaptive agentic framework that shifts the DocMT paradigm from static retrieval to dynamic parametric internalization. |
| Outcome: | Extensive experiments on the discourse-rich GuoFeng and IWSLT2017 datasets show that AdaDPI outperforms the SoTA baselines by more than 5 points on the consistency metric. |
Can Large Language Models Learn Translation Robustness from Noisy-Source In-context Demonstrations? (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been used for machine translation, but their robustness remains a challenge, as they struggle to translate sentences in the presence of noise even when using similarity-based in-context learning methods. |
| Approach: | They propose a scheme for studying machine translation robustness on LLMs by using noisy-source demonstration examples. |
| Outcome: | The proposed model can learn robustness from noisy-source demonstration examples, thereby improving translation performance on noisy sentences. |
Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing privacy protection frameworks for large language models are inadequate . however, training data for LLMs often contains sensitive or unauthorized information . |
| Approach: | They propose a framework that augments privacy data by automatically synthesizing new private data, which deactivates the first trigger to privacy seesaw issue. |
| Outcome: | The proposed framework can mitigate Privacy Seesaw in large language models by synthesizing new private data and adapting activation patching to privacy neuron editing for switching off the second trigger. |
CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models exhibit a risk propensity of more than 40%, and are prone to self-sustainability, power seeking and other dangerous goals as the size of models increases. |
| Approach: | They propose a Chinese dataset to gauge the risk proclivities inherent in large language models such as resource acquisition and malicious coordination. |
| Outcome: | The proposed dataset consists of 14,888 questions that simulate scenarios related to predefined 7 types of frontier risks. |
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation (2021.acl-short)
Copied to clipboard
| Challenge: | Existing work has increased the modeling capacity of multilingual NMT by deepening or widening the Transformer. |
| Approach: | They propose to increase the model capacity by deepening the Transformer . they propose to use a multi-input-multi-output architecture to combine multiple inputs . |
| Outcome: | The proposed model surpasses previous work and is 1.31 times faster than existing models. |
HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)
Copied to clipboard
Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong
| Challenge: | a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models . |
| Approach: | They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams . |
| Outcome: | The proposed model is based on o1-like models and a high-level model. |
TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks (2020.emnlp-main)
Copied to clipboard
| Challenge: | TED-CDB dataset is a unique corpus of spoken discourse in Chinese . TED is based on the concept that discourse relations are grounded in an identifiable set of discourse connectives or Altlex expressions. |
| Approach: | They have created a dataset that annotates TED talks in Chinese . they propose to adapt the dataset to Chinese news text to improve its performance . |
| Outcome: | The TED-CDB dataset can improve the performance of systems for languages other than Chinese . it is adapted to features that are not present in English and can extract discourse semantic features . |
Do Large Language Models Mirror Cognitive Language Processing? (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models have demonstrated remarkable abilities in text comprehension and logical reasoning. |
| Approach: | They employ Representational Similarity Analysis to measure alignment between 23 LLMs and fMRI signals of the brain. |
| Outcome: | The results show that training strategies affect the LLM-brain alignment. |
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for unsupervised text style transfer lack parallel data and difficulties in content preservation. |
| Approach: | They propose a neural approach to unsupervised text style transfer using non-parallel data. |
| Outcome: | The proposed approach can be trained end-to-end on two widely-used public datasets. |
KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base (2022.acl-long)
Copied to clipboard
| Challenge: | Existing semantic parsing frameworks for conversational question answering do not handle uncertain reasoning . qa over large knowledge bases has attracted broad interest due to the popularity of intelligent virtual assistants . |
| Approach: | They propose a fuzzy semantic parsing framework that defines fuzzy comparison operations in grammar for uncertain reasoning based on fuzzy set theory. |
| Outcome: | The proposed framework achieves significant improvements over state-of-the-art models on a large-scale conversational question answering benchmark. |
Rewiring the Transformer with Depth-Wise LSTMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Stacking non-linear layers allows deep neural networks to model complicated functions . but residual connections within each layer fail to fuse information from previous layers effectively . |
| Approach: | They propose a Transformer with depth-wise LSTMs connecting cascading Transformer layers and sub-layers. |
| Outcome: | The proposed model improves in English-German / French and multilingual tasks with BLEU. |
MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) based sparse architectures are prone to overfitting on low-resource language translation. |
| Approach: | They propose a modularized MNMT framework that flexibly assembles dense and MoE-based sparse modules to achieve the best of both worlds. |
| Outcome: | The proposed framework outperforms existing models on low-resource language translation and zero-shot translation on benchmark datasets. |
Is Robustness Transferable across Languages in Multilingual Neural Machine Translation? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have focused on bilingual machine translation with a single translation direction. |
| Approach: | They propose a robustness transfer analysis protocol to analyze the transferability of robustness across different languages in multilingual neural machine translation. |
| Outcome: | The proposed protocol shows that the robustness gained in one translation direction can transfer to other translation directions. |
Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for imbalanced text classification can generate anchor instances for difficult samples . difficult samples are hard to classify as they are embedded into an overlapping semantic region with the majority class. |
| Approach: | They propose a Mutual Information constrained Semantically Oversampling framework that generates anchor instances for difficult samples to help the backbone network determine the re-embedding position of a non-overlapping representation. |
| Outcome: | The proposed framework can generate anchor instances to help classifiers achieve significant improvements over baselines on a variety of imbalanced text classification tasks. |
BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels (D19-1)
Copied to clipboard
| Challenge: | Using BiPaR, we build monolingual, multilingual and cross-lingual MRC on novels. |
| Approach: | They propose a bilingual parallel novel-style machine reading comprehension dataset BiPaR . they collect 3,667 bilingual parallel paragraphs from Chinese and English novels . |
| Outcome: | The proposed dataset supports multilingual and cross-lingual reading comprehension. |
Thesis Proposal: Diagnosing and Mitigating Semantic Interference in Script-Sharing Low-Resource Language Models: A Case Study on Square Bai Script (2026.acl-srw)
Copied to clipboard
| Challenge: | Multilingual models cover more languages than ever, yet script-sharing low-resource languages remain vulnerable to failures driven by script and dominant-language priors. |
| Approach: | They propose to diagnose semantic interference in Square Bai Script, a script-sharing low-resource language . they will compare adaptation strategies under realistic compute constraints and estimate when shared-script transfer helps or harms adaptation. |
| Outcome: | The proposed model underperforms in a script-sharing low-resource setting because Bai is low-source and because it treats visible overlap as safe transfer by default. |
CS2W: A Chinese Spoken-to-Written Style Conversion Dataset with Multiple Conversion Types (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets focus on a single type of spoken style, such as disfluencies. |
| Approach: | They propose a Chinese Spoken-to-Written style conversion dataset with 7,237 spoken sentences extracted from transcribed conversational texts. |
| Outcome: | The proposed dataset covers four major conversion problems corresponding to the majority of spoken styles. |
Recovering Gold from Black Sand: Multilingual Dense Passage Retrieval with Hard and False Negative Samples (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to recover and utilize negative samples have not been effective on all languages. |
| Approach: | They propose a multilingual dense passage retrieval framework to recover and utilize negative samples. |
| Outcome: | The proposed framework outperforms strong sparse, dense and hybrid baselines on a high-quality dataset covering eleven typologically diverse languages. |
CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech-totext translation (ST) data are limited due to the limited resources. |
| Approach: | They propose a knowledge distillation framework for speech translation that integrates knowledge from machine translation and decouples knowledge from non-target class knowledge. |
| Outcome: | The proposed framework outperforms state-of-the-art models on a benchmark dataset. |
Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | a self-attention network can be easily parallelized at sequence level, but LSTMs are slower to train . a recent study shows that LS models require a lot of computations to perform . |
| Approach: | They propose to compute LSTMs at sequence level to enable sequence-level parallelization . they use a bag-of-words representation of the preceding tokens context to approximate LStms . |
| Outcome: | The proposed model performs better than existing models while being faster to train . the model can be trained efficiently due to the highly parallelized self-attention network . |
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models (2021.acl-long)
Copied to clipboard
| Challenge: | Using pretrained language models, we propose an error-annotated dataset for text generation . we use carefully selected prompt words to guide GPT-2 to generate candidate sentences . |
| Approach: | They propose an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models. |
| Outcome: | The proposed dataset covers 24 types of errors according to common sense and linguistics. |
Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing methods for robustness against homophone errors are limited to homophones . substitution errors are the most common errors in NMT models . |
| Approach: | They propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarially training for NMT models. |
| Outcome: | The proposed method improves on the clean test set and can be used in real-world scenarios. |
CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP (2022.acl-long)
Copied to clipboard
| Challenge: | Existing frameworks for transfer learning across tasks in natural language processing are CRA and CNM . CRA uses a correlation between brain-activity measurement and computational modeling to estimate task similarity with sentence representations. |
| Approach: | They propose a cognitively inspired framework to learn taxonomy for NLP tasks . they use Cognitive Representation Analytics and Cognitive-Neural Mapping . |
| Outcome: | The proposed framework can guide transfer learning across tasks in natural language processing without exhaustive pairwise task transferring. |
Long Text Generation with Topic-aware Discrete Latent Variable Model (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work focuses on the modeling of discourse relation, resulting in discrete codes learning shallow semantics. |
| Approach: | They propose a topic-aware latent code-guided text generation model that encourages discrete codes to model information about topics. |
| Outcome: | The proposed model generates more topic-relevant and coherent texts. |
Sentence Weighting for Neural Machine Translation Domain Adaptation (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has achieved satisfactory performance on many language pairs with various advantages over statistical machine translation. |
| Approach: | They propose a new sentence weighting method for the domain adaptation of neural machine translation that uses a domain similarity metric to evaluate the relevance of sentences to the target domain. |
| Outcome: | The proposed method achieves significant improvement over baselines on Chinese-English TED task and synthetic training task with only synthetic training parallel data. |
LFED: A Literary Fiction Evaluation Dataset for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | LFED is a literary fiction evaluation dataset for large language models that evaluate the capability of LLMs on the long fiction comprehension and reasoning. |
| Approach: | They propose a Literary Fiction Evaluation Dataset to evaluate LLMs' comprehension and reasoning on long fictions. |
| Outcome: | The proposed dataset evaluates the capability of large language models on the long fiction comprehension and reasoning. |
Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation (2026.acl-long)
Copied to clipboard
Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Deyi Xiong
| Challenge: | Current systems often fall short of this goal in settings where translation hinges on culturally grounded entities such as books, films, places, songs and idioms. |
| Approach: | They propose a framework that anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization. |
| Outcome: | The proposed framework improves on XC-Translate and shows that it can learn a robust reasoning process rather than imitating reference translations. |
PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Image translation is a task that translates an image containing text in the source language to the target language. |
| Approach: | They propose an end-to-end image translation framework that bridges the modality gap between visual inputs and textual inputs/outputs of machine translation (MT). |
| Outcome: | The proposed framework outperforms existing models on a large-scale image translation corpus . it significantly outperformed both cascaded and strong models on the e-commerce domain . |
Neural Machine Translation with Decoding History Enhanced Attention (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation with source-side attention has been criticized for its poor memory performance. |
| Approach: | They propose to use a Decoding History Enhanced Attention mechanism to render NMT models better at selecting both source-side and target-side information. |
| Outcome: | The proposed model improves by 0:9 BLEU on Chinese-English translation and the state-of-the-art on a larger task. |
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment (2026.findings-acl)
Copied to clipboard
Tianyu Dong, Yangyang Liu, Jiang Zhou, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Shaolin Zhu, Deyi Xiong
| Challenge: | Low-resource language tokens are often routed to different experts than those activated by high-resourced inputs, which hinders their efficacy in multilingual contexts. |
| Approach: | They propose a framework to transfer specialized capabilities from high-resource languages as anchors to low-resourced languages by using a symmetric Jensen-Shannon constraint. |
| Outcome: | The proposed framework outperforms standard instruction tuning on 5 low-resource languages and 3 benchmarks. |
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets for word prediction with long-range context have not been tested. |
| Approach: | They propose automatic and manual selection strategies tailored to Chinese to ensure that target words can only be predicted with long-term context. |
| Outcome: | The proposed model is 45 points behind human in terms of top-1 word prediction accuracy. |
CoDoNMT: Modeling Cohesion Devices for Document-Level Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to document-level neural machine translation focus on integrating context into translation, but they focus on the way of integrating contextual information into translation. |
| Approach: | They propose a document-level neural machine translation framework that models cohesion devices from two perspectives: Cohesion Device Masking and Cohetion Attention Focusing. |
| Outcome: | The proposed model outperforms state-of-the-art document-level neural machine translation baselines on three benchmark datasets. |
Language Branch Gated Multilingual Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to multilingual neural machine translation do not allow knowledge transfer across languages. |
| Approach: | They propose a language branch gated multilingual neural machine translation module that encourages knowledge transfer within the same language branch. |
| Outcome: | The proposed approach significantly improves translation quality on middle- and low-resource languages over previous methods. |
Towards Optimal Evaluation Efficiency for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) require large-scale benchmarks, which are costly in terms of time, computational resources, or API tokens. |
| Approach: | They propose an efficient evaluation framework that selects a question subset based on pre-tested results and uses semantic analysis to evaluate whether the subset preserves the original benchmark. |
| Outcome: | The proposed evaluation framework outperforms previous methods in reliability and score accuracy. |
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)
Copied to clipboard
Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong
| Challenge: | Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process. |
| Approach: | They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods . |
| Outcome: | The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality. |
HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language models (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models tend to rely on shortcut features that spuriously correlate with labels for prediction, which weakens their generalization on out-of-distribution samples. |
| Approach: | They propose a human attention guided approach to identifying shortcut learning that encourages the LLM-based target model to learn relevant features by exploring both human and neural attention. |
| Outcome: | The proposed approach improves the robustness of large language models on out-of-distribution (OOD) samples while not affecting the performance on IID data. |
Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation systems translate one sentence at a time, ignoring inter-sentence information. |
| Approach: | They propose an inter-sentence gate model that uses the same encoder to encode two adjacent sentences . it captures the connection between sentences and fuses recency from neighboring sentences a model proposes . |
| Outcome: | The proposed model improves on NIST Chinese-English translation tasks . it captures the connection between sentences and fuses recency from neighboring sentences . |
Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on sentence-level translation have focused on document level machine translation (DOCMT) document level translation is a complex task different from sentence- level translation. |
| Approach: | They propose a Context-Aware Prompting method which generates more accurate, coherent translations via in-context learning. |
| Outcome: | The proposed method is effective in literary translation tasks and zero pronoun translation tasks. |
Modeling Long Context for Task-Oriented Dialogue State Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to dialogue state tracking are limited to scenarios with infinite slot values and prediction of unseen slot values. |
| Approach: | They propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation. |
| Outcome: | The proposed model achieves state-of-the-art accuracy on the MultiWOZ 2.0 dataset. |
LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing benchmarks for comprehensively evaluating Chinese Large Language Models are insufficient. |
| Approach: | They propose a Large-scale, Holistic, and Multi-subject Knowledge Evaluation benchmark to evaluate Chinese Large Language Models. |
| Outcome: | The proposed benchmark measures the knowledge acquisition capabilities of Chinese Large Language Models across 75 subjects from primary school to professional certification exams. |
MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated strong performance even with limited parallel data. |
| Approach: | They propose a multiple language-aware LoRA knowledge transfer framework that selectively adapts LLMs to MT by transferring knowledge from a large teacher to a small student model. |
| Outcome: | The proposed framework outperforms baseline models on multilingual language pairs by +1.7 BLEU on average. |
Inverse Reinforcement Learning for Text Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that inverse reinforcement learning (RL) training has certain disadvantages such as object mismatch and exposure bias. |
| Approach: | They propose inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models. |
| Outcome: | The proposed model outperforms MLE and RL baselines on ROUGE, coverage, novelty, compression ratio, factuality, and human evaluations. |
Learning Structural Information for Syntax-Controlled Paraphrase Generation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Syntax-controlled paraphrase generation aims to produce paraphrase conform to given syntactic patterns. |
| Approach: | They propose a model that captures parent-child and sibling relations and a syntax encoder to capture alignment relations. |
| Outcome: | The proposed model achieves state-of-the-art in terms of semantic and syntactic quality on two popular benchmark datasets. |