Papers by Fan Yin

27 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.
Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025.acl-long)

Copied to clipboard

Challenge: Evidence retrieval is used to enhance Large Language Models (LLMs) but in real-world applications, it often returns lengthy documents with redundant or irrelevant content, confusing downstream readers.
Approach: They propose a framework that reformulates evidence retrieval as a dynamic tree expansion process.
Outcome: The proposed framework outperforms existing methods on five datasets.
On the Robustness of Language Encoders against Grammatical Errors (2020.acl-main)

Copied to clipboard

Challenge: Pre-trained language encoders are effective in facilitating downstream natural language processing tasks, but they often assume training and test corpora are clean and it is unclear how the models behave when confronted with noisy input.
Approach: They conduct adversarial attacks to simulate grammatical errors on clean text data.
Outcome: The proposed model performs better when confronted with natural grammatical errors than when faced with noisy input.
UniLG: A Unified Structure-aware Framework for Lyrics Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing works ignore musical attributes hidden behind lyrics and structure of lyrics . existing works ignore structure of generated lyrics and do not consider structure of songs .
Approach: They propose a framework for conditional lyrics generation that considers structure and relationship between lyrics and music.
Outcome: The proposed framework improves the structure modeling and unifies different conditions for different types of lyrics generation.
Efficient Shapley Values Estimation by Amortization for Text Classification (2023.acl-long)

Copied to clipboard

Challenge: Shapley Values are often estimated with a small number of stochastic model evaluations, but this can only be mitigated by aggregating thousands of model evaluation.
Approach: They propose to combine a model with thousands of model evaluations to estimate Shapley Values without additional model evaluation.
Outcome: The proposed model estimates Shapley Values accurately with up to 60 times speedup compared to traditional methods and does not suffer from stability issues as inference is deterministic.
LLM-REDIAL: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with LLMs (2024.findings-acl)

Copied to clipboard

Challenge: Existing CRS datasets suffer from data inextensibility and semantic inconsistency .
Approach: They introduce the LLM-REDIAL dataset to facilitate the research in CRS by leveraging large language models to generate high-quality dialogues.
Outcome: The proposed dataset is the largest multi-domain CRS dataset which consists of 47.6k multi-turn dialogues with 482.6k utterances across 4 domains.
WESR: A Benchmark and Strong Baseline for Word-level Event-Speech Recognition (2026.findings-acl)

Copied to clipboard

Challenge: aaron carroll: the precise localization of non-verbal vocal events remains a critical yet under-explored challenge. carroll says current methods suffer from insufficient task definitions with limited category coverage. carrol: knowing exactly where an event occurred is not enough; knowing exactly what it happened is.
Approach: They propose a taxonomy of 21 vocal events with a new categorization into discrete versus continuous types.
Outcome: The proposed model disentangles ASR errors from event detection while maintaining ASR quality.
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks (2023.emnlp-main)

Copied to clipboard

Challenge: Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models on diverse tasks with instructions.
Approach: They propose a framework to identify informative tasks and then actively tune models on selected tasks.
Outcome: The proposed method outperforms baseline strategies for task selection on NIV2 and Self-Instruct datasets.
On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning (2026.acl-long)

Copied to clipboard

Challenge: Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and verbal goals.
Approach: They propose an On-policy Reinforcement fine-tuning framework with offline rewards for Embodied Task Planning that preserves generalization benefits of RFT while addressing costly interaction and sparse rewards.
Outcome: The proposed framework outperforms closed-source and online-RL methods on EmbodiedBench, a recent benchmark for interactive embodied tasks.
TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies on large language models (LLMs) focus on basic plan validity, but neglect critical aspects such as route efficiency, POI appeal, and real-time adaptability.
Approach: They propose a benchmark for retrieval-augmented, spatiotemporal-aware travel planning that integrates retrieved trajectories with LLMs’ intrinsic reasoning.
Outcome: The proposed framework improves spatial efficiency and POI rationality while challenging universality and robustness due to conflicting references and noisy data.
ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods show poor performance under Far Boundary (FB) adversarial examples.
Approach: They propose to use a new technique to detect adversarial examples based on data and model uncertainty to outperform existing methods.
Outcome: The proposed method outperforms existing methods by 3.6 and 6.0 AUC points under each scenario.
DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to planning involve implicit planning or introduce explicit planners without systematically optimizing the planning stage.
Approach: They propose an end-to-end RL framework that enhances the planning capabilities of deep research agents.
Outcome: Experiments show that DeepPlanner improves planning quality and achieves state-of-the-art results under a lower training budget.
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for instruction tuning do not include associating instructions with existing datasets.
Approach: They propose a dynamic growth paradigm for the automatic curation of instruction-tuning data . they use existing datasets to automatically construct instruction-uning datasets .
Outcome: The proposed model reduces the API cost for generating instructions and provides high-quality data.
Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning (2023.acl-long)

Copied to clipboard

Challenge: Large language models have shown impressive performance in following natural language instructions to solve unseen tasks.
Approach: They propose two strategies to help large language models better leverage task instructions . they propose to remove 60% of tokens from the task definitions while maintaining model performance .
Outcome: The proposed approach achieves 4.2 Rouge-L improvement over 119 unseen test tasks.
Contrastive Instruction Tuning (2024.findings-acl)

Copied to clipboard

Challenge: Current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles.
Approach: They propose a method which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarities between semantically different ones.
Outcome: Experiments on the PromptBench benchmark show that Contrastive Instruction Tuning improves LLMs’ robustness to unseen instructions with variations across character, word, sentence, and semantic levels by +2.5% in accuracy.
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.
Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have produced significant advances in the field of recommender systems.
Approach: They propose to retrieve up-to-date structure information from the knowledge graph to augment recommendations by leveraging external knowledge sources.
Outcome: Experiments on a large dataset show that the proposed method is effective in enhancing LLM-based recommendations.
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.
NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach: They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome: The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.
Entity-Relation Extraction as Multi-Turn Question Answering (P19-1)

Copied to clipboard

Challenge: Identifying entities and their relations is the prerequisite of extracting structured knowledge from unstructured raw texts.
Approach: They propose a new paradigm for the task of entity-relation extraction . they cast the task as a multi-turn question answering problem .
Outcome: The proposed paradigm significantly outperforms previous best models on the ACE and CoNLL04 datasets.
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Challenge: a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach: They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome: The proposed agents are based on operating systems (OS) and operating systems frameworks.
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning (2024.findings-emnlp)

Copied to clipboard

Challenge: Fine-tuning and in-context learning are two prevalent methods in imbuing large language models with task-specific knowledge.
Approach: They propose to use a circuit shift theory to explain why in-context learning is superior to fine-tuning for tasks with implicit patterns.
Outcome: The proposed method can grasp deep patterns and significantly improve accuracy on implicit patterns, compared with fine-tuning and in-context learning.
Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies show that RALMs generate baseless information or contradicts with the retrieved context.
Approach: They propose a lightweight monitor that leverages fine-grained decoding dynamics to synchronously detect unfaithful sentences.
Outcome: Empirical results show that SynCheck outperforms baseline faithfulness detection and FOD outperformed traditional strategies in terms of faithfulness.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing models fail to capture and model customer intention effectively because of insufficient information exploitation and only apparent information like descriptions and titles are used.
Approach: They propose to exploit existing session data to capture and model intention in E-commerce product purchase sessions using a multimodal benchmark.
Outcome: The proposed framework can bridge the gap between intention understanding in simplified research cases like co-buy intention and more complex yet practical scenarios like session history.
On the Sensitivity and Stability of Model Interpretations in NLP (2022.acl-long)

Copied to clipboard

Challenge: Recent years have witnessed the emergence of post-hoc interpretations that aim to uncover how NLP models make predictions.
Approach: They propose two new criteria that provide complementary notions of faithfulness to removal-based criteria.
Outcome: The proposed methods overcome limitations of gradient-based methods on removal-based criteria and overcome limitations in the proposed methods.
Answering Complex Geographic Questions by Adaptive Reasoning with Visual Context and External Commonsense Knowledge (2025.acl-long)

Copied to clipboard

Challenge: a new task of answering geographic reasoning questions based on the given image is proposed . the task requires identifying the objects in the image and understanding the background context .
Approach: They propose a task of answering geographic reasoning questions based on the given image . they analyze the image and describe its fine-grained content by text and keywords .
Outcome: The proposed method can be used to answer geographic reasoning questions based on an image . it can be applied to a large-scale dataset with 41,329 samples .

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