Papers by Jun Yin

18 papers
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation (2025.acl-long)

Copied to clipboard

Challenge: Large language models have been shown to be effective in multi-turn interactions . however, their performance may be limited in complex, multi-turned interactions involving users and multiple tools.
Approach: They propose a framework for synthesizing high-quality training trajectories to enhance the function calling capability of large language model agents in multi-turn conversations with humans.
Outcome: The proposed model outperforms the teacher model by 68.01 on BFCL-v3 and 73.30 on ToolQuery.
Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)

Copied to clipboard

Challenge: Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time.
Approach: They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts .
Outcome: The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines.
Xiaomingbot: A Multilingual Robot News Reporter (2020.acl-demos)

Copied to clipboard

Challenge: Xiaomingbot is a multilingual and multimodal software robot with four capabilities: news generation, news translation, news reading and avatar animation.
Approach: They propose to build a multilingual and multimodal software robot with four inte- gal capabilities: news generation, news translation, news reading and avatar animation.
Outcome: The proposed system generates Chinese news, then reads it in multiple languages and generates an animated avatar reading it.
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Challenge: Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach: They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome: The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .
Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination (D18-1)

Copied to clipboard

Challenge: Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model.
Approach: They propose to use mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains.
Outcome: The proposed model distinguishes and exploits word-level domain contexts on Chinese-English and English-French translation tasks.
Learning to Translate by Translating: Stabilizing the Dual Loop via Semantic-Aware Self-Evolution (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been successful in machine translation, but lack of high-quality parallel corpora and cost constrain scalability.
Approach: They propose an LLM-driven dual-learning framework that enables autonomous translation . they employ a robust semantic-aware reward function that balances adequacy with reconstruction fidelity .
Outcome: The proposed model outperforms larger models on benchmarks and achieves parity with state-of-the-art supervised baselines on mainstream benchmarks.
CARD: Cross-modal Agent Framework for Generative and Editable Residential Design (2025.emnlp-main)

Copied to clipboard

Challenge: Architectural design automation has made significant progress, but the complexity of open-world environments makes residential design a challenging task.
Approach: They propose a framework that leverages a system of specialized cross-modal agents to adapt to open-world residential design.
Outcome: The proposed framework enables users to generate and edit residential design without requiring specialized expertise.
FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing evaluation methods for floor plan generation rely on statistical metrics like FID, GED, and PSNR, which fail to evaluate using domain knowledge.
Approach: They propose to use a first floor plan dataset to train a floor plan generation model based on a multi-dimensional preference score and a textual analysis to integrate architects’ professional expertise and preferences.
Outcome: The proposed model outperforms baseline models in text-conditional and class-condition tasks and is more rational and aligns better with human preferences.
Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across various vision reasoning tasks.
Approach: They propose a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations.
Outcome: The proposed language achieves state-of-the-art parsing performance and significantly boosts MLLMs’ capabilities for downstream geometry reasoning tasks.
MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching (2026.acl-long)

Copied to clipboard

Challenge: Existing reinforcement learning methods rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory.
Approach: They propose a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation.
Outcome: The proposed framework surpasses the majority of 8B competitors on three benchmarks.
Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing efforts to estimate document utility rely on downstream generation performance, which conflates the influence of external documents with the intrinsic knowledge of the LLM.
Approach: They propose an uplift-based definition of document utility that quantifies each document’s marginal benefit over the LLM’s internal knowledge.
Outcome: The proposed framework improves the performance of the LLM by incorporating external retrieved documents into the model.
Few Shot Rationale Generation using Self-Training with Dual Teachers (2023.findings-acl)

Copied to clipboard

Challenge: Existing models that generate free-text explanations for annotated labels are expensive and require a large annotation dataset.
Approach: They propose a self-training approach leveraging both labeled and unlabeled data to further improve few-shot models by combining teacher models and a multi-tasking student model.
Outcome: The proposed model improves on three public datasets and can generate a free-text explanation for predicted labels.
PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)

Copied to clipboard

Challenge: Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations.
Approach: They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments.
Outcome: The proposed method has been deployed in a real-world commercial search system.
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to inject safety-aligned large language models rely on token-level mappings, which do not guarantee sustained harmful output.
Approach: They propose a method that directly modifies model weights to map a trigger to an attacker-specified response.
Outcome: The proposed method achieves high triggered attack success while maintaining non-triggered safety and general utility.
UEGP: Unified Expert-Guided Pre-training for Knowledge Rekindle (2024.findings-naacl)

Copied to clipboard

Challenge: Existing paradigms for pre-training and fine-tuning have limitations . knowledge rekindle aims to break through performance upper bounds of experts without introducing additional annotated data.
Approach: They propose a new paradigm for pre-training and fine-tuning that aims to re-incorporate the fine- tuned expert model into the training cycle and break through performance upper bounds of experts.
Outcome: The proposed model breaks through performance upper bounds of experts without additional annotated data.
Meta Distant Transfer Learning for Pre-trained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Notable PLMs are available for text classification tasks, but performance of PLM on downstream tasks may be limited by the availability of training set.
Approach: They propose a meta-learning framework to learn the transferable knowledge across tasks using PLMs.
Outcome: The proposed framework outperforms baselines on seven datasets and is task-agnostic and unbiased.
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.
Target-based Sentiment Annotation in Chinese Financial News (2020.lrec-1)

Copied to clipboard

Challenge: Using a large corpus of 8,314 target-level sentiment annotations, sentiment classification on multiple opinion aspects/targets level is unsatisfactory.
Approach: They propose to construct a large-scale target-based sentiment annotation corpus on Chinese financial news text.
Outcome: The proposed corpus has 8,314 target-level sentiment annotations on Chinese financial news text.

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