Papers by Meng Yan

26 papers
Disentangling the Roles of Target-side Transfer and Regularization in Multilingual Machine Translation (2024.eacl-long)

Copied to clipboard

Challenge: Multilingual Machine Translation (MMT) benefits from knowledge transfer across different language pairs, but performance differences between one-to-many and many-to-1 translation are negligible.
Approach: They conduct a large-scale study that varies the auxiliary target-side languages along two dimensions to show the dynamic impact of knowledge transfer on the main language pairs.
Outcome: The proposed model can translate between multiple languages with minimal positive transfer ability.
Selective Knowledge Distillation for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Neural Machine Translation models achieve state-of-the-art performance on many translation benchmarks.
Approach: They propose a protocol that analyzes different impacts of samples by comparing various samples’ partitions.
Outcome: The proposed methods yield up to +1.28 and +0.89 BLEU points improvements over the Transformer baseline, respectively.
Parameter-Efficient Fine-Tuning without Introducing New Latency (2023.acl-long)

Copied to clipboard

Challenge: Parameter-efficient fine-tuning of pre-trained language models has been demonstrated to be effective, but its inherent characteristics limit its performance.
Approach: They propose to generate a sparse mask in a task-agnostic manner by modifying only a small subset of existing parameters and adding new parameters.
Outcome: The proposed method surpasses existing methods on the GLUE benchmark by a significant margin.
Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level (2024.emnlp-main)

Copied to clipboard

Challenge: General-purpose Large Language Models (LLMs) like GPT-4 have exhibited strong translation abilities.
Approach: They propose to use a model-agnostic model to refine the performance of general-purpose large-language models for machine translation (MT) by utilizing Gemma-2B/7B as the backbone.
Outcome: The proposed model-agnostic and cost-effective tool improves the performance of general-purpose large-language models for machine translation (MT) by integrating it with any general-use LLM.
How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise in Machine Translation (2025.findings-naacl)

Copied to clipboard

Challenge: Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems.
Approach: They propose a process for simulating misalignment controlled by semantic similarity which closely resembles misaligned sentences in real-world web-crawled corpora.
Outcome: The proposed model significantly improves translation performance in the presence of misalignment noise and when applied to real-world, noisy web-mined datasets, across a range of translation tasks.
How Far can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data (2024.findings-acl)

Copied to clipboard

Challenge: a common solution to zero-shot translation is to add as many related translation directions as possible to the training corpus.
Approach: They show that a small amount of multi-parallel data can achieve significant zero-shot improvements . they say that the resulting non-English performance is close to the complete translation upper bound .
Outcome: The proposed model achieves +21.7 ChrF++ non-English translation improvements on EC30 dataset . the resulting non- English performance exceeds M2M100 by an average of 5.9 ChrF+ .
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) can replicate insecure patterns from training data.
Approach: They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module.
Outcome: Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines.
Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography (2026.acl-long)

Copied to clipboard

Challenge: linguistic steganography assumes that stegographic texts are fragile to even minor modifications, compromising text quality.
Approach: They propose an anchored sliding window framework to improve imperceptibility and robustness . they propose to include the prompt and a bridge context within the context window .
Outcome: The proposed framework outperforms the baseline method in text quality, imperceptibility and robustness across diverse settings.
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases (2021.acl-long)

Copied to clipboard

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 .
MultiCodeAttack: Iterative Jailbreak Attacking on LLMs with Multi-Code Prompt Injection (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to jailbreak rely on fixed template design and a single programming language . however, existing approaches do not consider language diversity or adaptive template evolution .
Approach: They propose a structured jailbreak framework that explores and optimizes multi-language code templates.
Outcome: The proposed framework outperforms existing jailbreak baselines and produces higher harmful outputs than baseline methods.
Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it difficult to identify model limitations.
Approach: They propose to use Agri-CM3 to assess multi-level reasoning in agricultural management by integrating multiple data modalities.
Outcome: The Agri-CM3 benchmark includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations.
From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach: They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome: The proposed method improves egocentric reasoning abilities on six tasks.
Event Detection with Multi-Order Graph Convolution and Aggregated Attention (D19-1)

Copied to clipboard

Challenge: Existing methods for event detection use first-order syntactic relations to identify trigger words.
Approach: They propose a dependency tree-based method to model and aggregate multi-order syntactic representations in sentences.
Outcome: The proposed method outperforms existing methods on a benchmark dataset . it uses a dependency tree based graph convolution network with aggregative attention .
DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for decoding target language are degenerate, hallucinating or empty.
Approach: They propose a method that tunes down the Softmax temperature to reduce autoregressive over-smoothness by label smoothing the output distributions.
Outcome: The proposed method improves MBR in various settings.
Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space (2022.emnlp-main)

Copied to clipboard

Challenge: Current evaluation of neural machine translation systems is limited by one best hypothesis and search errors brought by heuristic decoding algorithms.
Approach: They propose a new evaluation protocol which defines model errors with model’s ranking capability over hypothesis space and Monte Carlo sampling evaluation to tackle the problem of exponentially large space.
Outcome: The proposed evaluation protocol is consistent with what is currently used in the field and is consistent to what is being proposed.
Improving the Robustness of Large Language Models via Consistency Alignment (2024.lrec-main)

Copied to clipboard

Challenge: Large language models have shown tremendous success in following user instructions and generating helpful responses, but their robustness is still far from optimal.
Approach: They propose a two-stage training framework that helps a model generalize on following instructions via similar instruction augmentations.
Outcome: The proposed training framework improves diversity and aligns the model with human expectations by differentiating subtle differences in similar responses.
Monotonic Paraphrasing Improves Generalization of Language Model Prompting (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable proficiency in zero-shot decision making and instruction following.
Approach: They propose an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt rewriting, and a target LM that constrains the generation for lower perxity.
Outcome: The proposed method can efficiently paraphrase the original prompt without altering its semantic meaning while decreasing the perplexity of each generation as calculated by the target LM.
Rethinking the Word-level Quality Estimation for Machine Translation from Human Judgement (2023.findings-acl)

Copied to clipboard

Challenge: Word-level Quality Estimation (QE) of Machine Translation aims to detect potential translation errors in the translated sentence without reference.
Approach: They propose to use a human-generated translation judgment to generate a word-level quality estimate (QE) using a translation error rate toolkit to detect translation errors without reference.
Outcome: The proposed dataset is more consistent with human judgment and confirms the effectiveness of the proposed tag-correcting strategies.
Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots (2020.emnlp-main)

Copied to clipboard

Challenge: Open-vocabulary slots degrade neural-based slot filling models because they can take on unlimited set of values and have no semantic restriction nor length limit.
Approach: They propose a model-agnostic slot filling method that explicitly decouples local semantics inherent in open-vocabulary slot words from the global context.
Outcome: The proposed method outperforms other models on open-vocabulary slots without deteriorating performance.
RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies on social media text processing do not focus on responsive emotion analysis.
Approach: They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China.
Outcome: The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China.
Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method (2024.naacl-long)

Copied to clipboard

Challenge: Recent literature reveals that Large Language Models (LLMs) hallucinate intermittently, which impedes their reliability for further utilization.
Approach: They propose a self-detection method to detect which questions an LLM does not know by combining the two components to identify whether the model generates a non-factual response to the question.
Outcome: The proposed method can detect which questions an LLM does not know across factoid question-answering, arithmetic reasoning, and commonsense reasoning tasks.
A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph (2020.findings-emnlp)

Copied to clipboard

Challenge: Topic-to-essay generation is a promising task for natural language generation.
Approach: They propose a Sentiment Controllable topic-to- essay generator with a Topic Knowledge Graph enhanced decoder to generate essays with only several given topic words.
Outcome: The proposed model outperforms the state-of-the-art model on automatic and human evaluation.
SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for supervised fine-tuning are limited due to labeled data . existing methods require long adaptation times and batch statistics are unavailable in streaming settings .
Approach: They propose a plug-and-play, signer-aware Mixture-of-Experts (MoE) TTA architecture for SLT . they use a combination of lightweight MoE modules and unsupervised regularizers to decouple domain shift .
Outcome: The proposed test-time adaptation outperforms existing TTA methods in sign language translation . the proposed architecture can be used in real-world deployments without labeling .
DiQAD: A Benchmark Dataset for Open-domain Dialogue Quality Assessment (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on dialogue quality assessment are uncapable of providing an end-to-end and human-epistemic assessment dataset . open-domain dialogue assessment is complicated and costly, but it can be done by recruiting human evaluators.
Approach: They propose a large-scale dialogue quality assessment dataset for automatically assessing open-domain dialogue quality.
Outcome: The proposed dataset is openly accessible at https://github.com/yukunZhao/Dialogue_quality_evaluation.
Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models (2025.findings-emnlp)

Copied to clipboard

Challenge: lightweight plug-and-play framework that encodes backdoor fingerprints into LoRA adapters .
Approach: proposed framework encodes backdoor fingerprints into LoRA adapters via constrained fine-tuning . enables seamless fingerprint transplantation through parameter fusion, eliminating full-parameter updates while maintaining integrity.
Outcome: The proposed framework achieves superior robustness against various scenarios while reducing computational overhead compared to traditional approaches.
Multi-Unit Transformers for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that the MUTE models outperform the Transformer-Base by up to +1.52, +1.99 and +1.00 BLEU points, with only a mild drop in inference speed (about 3.1%).
Approach: They propose to use multiple parallel units to promote the expressiveness of the Transformer by introducing diverse and complementary units.
Outcome: The proposed models outperform the Transformer-Base model with only a mild drop in inference speed (about 3.1%).

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations