Papers by Tan Yan

19 papers
Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing studies on multi-modal neural machine translation focus on visual information, but text and image may not match exactly, and visual noise is often ignored.
Approach: They propose a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT.
Outcome: The proposed model achieves state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.
Cross-Lingual Phrase Retrieval (2022.acl-long)

Copied to clipboard

Challenge: Existing approaches to cross-lingual phrase retrieval learn word or sentence representations in word or sentences.
Approach: They propose a cross-lingual phrase retrieval model that extracts phrase representations from unlabeled example sentences.
Outcome: The proposed model outperforms state-of-the-art methods on a large-scale cross-lingual phrase retrieval dataset, showing it can perform in an unseen language pair during training.
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+ .
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach: They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome: The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .
LiGen: Active Lipid Generation via a Molecular Language Model (2026.acl-long)

Copied to clipboard

Challenge: Lipid nanoparticles (LNPs) can deliver cargos to tumor and immune cells . traditional approaches rely on experimental screening and expert judgment .
Approach: They propose a method to generate lipid molecules efficiently and actively using deep learning.
Outcome: The proposed method outperforms baseline methods on multiple cell lines and achieves a 30% improvement over the current methods.
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations.
Approach: They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval.
Outcome: The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model.
Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for LLM-based mobile agents are insufficient to evaluate their capabilities.
Approach: They propose a benchmark to evaluate LLM-based mobile agents' planning capabilities . they expand UI operations by incorporating 103 APIs to accelerate task completion .
Outcome: The proposed benchmarks are based on 103 collected APIs and real user queries . the data is categorized into three distinct groups: SAST, SAMT, and MAMT .
What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time (2026.acl-long)

Copied to clipboard

Challenge: Existing TTRL methods rely on positive pseudo-labeling strategies to enhance reasoning capabilities.
Approach: They propose a test-time reinforcement learning framework that mitigates label noise amplification by deriving pseudo-rewards from majority voting consensus.
Outcome: The proposed framework mitigates label noise amplification by implementing selective positive pseudo-labeling and entropy-gated negative p-labeled pruning.
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains.
Approach: They propose a training framework that operationalizes this principle through coarse-to-fine budgeting.
Outcome: Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines.
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Copied to clipboard

Challenge: Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach: They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome: The proposed framework improves performance of commercial and open-source models.
Incorporating Causal Analysis into Diversified and Logical Response Generation (2022.coling-1)

Copied to clipboard

Challenge: Existing generation-based models generate generic and safe responses such as "So am I" or "I don't know"
Approach: They propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediator into generating process.
Outcome: The proposed model generates relevant and informative responses and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.
TimelineQA: A Benchmark for Question Answering over Timelines (2023.findings-acl)

Copied to clipboard

Challenge: Existing question answering techniques for lifelogs do not provide accurate answers . augmented reality glasses have led to the creation of personal assistants .
Approach: They propose to use a benchmark to query lifelogs to find out what happened in real life . they find that extractive QA systems out-perform retrieval-augmented QA techniques .
Outcome: The proposed method outperforms state-of-the-art retrieval-augmented QA systems in atomic queries and multi-hop queries.
NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms.
Approach: They propose a visual-target trajectory collection pipeline that generates trajectories for GUI and embodied tasks using a single formulation.
Outcome: The proposed agent outperforms state-of-the-art agents in GUI navigation, spatial affordance prediction, and embodied navigation.
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring (2026.acl-long)

Copied to clipboard

Challenge: Existing efforts to mitigate this via token compression fail due to its autoregressive nature . linguistically redundant tokens are erroneously pruned, leading to hallucinations .
Approach: They propose a method that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem.
Outcome: Experiments on Qwen2-VL and Llama-3.2 families show that the proposed model achieves a speedup with negligible accuracy loss.
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models exhibit remarkable generative capabilities but can be misused for harmful purposes.
Approach: They propose a framework that transforms natural language inputs into code inputs.
Outcome: The proposed framework bypasses the safety guardrails of all models more than 80% of the time.
Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing (2026.findings-acl)

Copied to clipboard

Challenge: Existing knowledge editing methods rely on strict orthogonal projection to preserve previously edited knowledge, but this constraint limits gradient expressiveness, resulting in degradation of model generalization and overall performance as the number of edits increases.
Approach: They propose a method that leverages Singular Value Decomposition to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance"
Outcome: Extensive experiments on five mainstream LLMs show that the proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks.
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Copied to clipboard

Challenge: a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach: They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome: The proposed benchmarks show that the current models perform worse than the human ceiling.
ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation (2022.acl-long)

Copied to clipboard

Challenge: generative dialogue models use dialogue histories to generate the response . however, generating a response based on the historical information is not easy .
Approach: They propose a framework that utilizes simulated dialogue futures to enhance response generation.
Outcome: The proposed framework can generate better responses over strong baselines on two open-domain dialogue datasets.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

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