Papers by Yan Gong

26 papers
Graph-Structured Speculative Decoding (2024.findings-acl)

Copied to clipboard

Challenge: Speculative decoding is a promising technique to accelerate the inference of Large Language Models.
Approach: They propose a method that uses a token graph to record multiple sequence hypotheses within a single draft stage.
Outcome: The proposed method significantly accelerates the inference of Large Language Models (LLMs) it allows the LLM to choose from and select the longest sequence that meets its standards.
GMFL: Efficient Global Masking for Federated LLM Fine-tuning (2026.acl-long)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) has emerged as a prominent solution to mitigate the communication and computation costs in federated fine-tuning of Large Language Models (LLMs).
Approach: They propose a plug-and-play layer freezing mechanism to integrate with existing federated fine-tuning frameworks.
Outcome: The proposed solution reduces communication overhead and lowers computational costs while preserving the performance of the underlying federated fine-tuning methods.
Improving Input-label Mapping with Demonstration Replay for In-context Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: In-context learning (ICL) is an emerging capability of large autoregressive language models where a few demonstrations are appended to the input to enhance the model’s understanding of downstream NLP tasks without directly adjusting the model parameters.
Approach: They propose a method where a few demonstrations are appended to the input to enhance the model's understanding of downstream NLP tasks without directly adjusting the model parameters.
Outcome: The proposed method significantly improves the input-label mapping in ICL demonstrations.
Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Copied to clipboard

Challenge: Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach: They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome: The proposed model achieves state-of-the-art performance on long-context benchmarks.
Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules (2024.emnlp-main)

Copied to clipboard

Challenge: Empirical results show that MoMs consistently outperform vanilla transformers .
Approach: They propose an architecture that allows for a mixture-of-modules computation that uses a finite set of modules defined by multi-head attention and feed-forward networks.
Outcome: The proposed architecture outperforms vanilla Transformers and their variants in multiple ways.
Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to improve machine reading comprehension performance on low resource languages are limited due to the lack of sufficient training data.
Approach: They propose to use a mixed MRC task to translate the question to other languages and build cross-lingual question-passage pairs.
Outcome: The proposed task improves on two cross-lingual MRC datasets.
ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing sequence-to-sequence models are optimized for future n-gram prediction and n stream self-attention mechanism.
Approach: They propose a self-supervised objective called future n-gram prediction and the proposed n stream self-attention mechanism to optimize the model for sequence-to-sequence learning.
Outcome: The proposed model achieves state-of-the-art on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks compared to the models using the same scale pre-training corpus.
GovScape: A Public Multimodal Search System for 70 Million Pages of Government PDFs (2026.acl-demo)

Copied to clipboard

Challenge: Efforts over the past three decades have produced web archives containing billions of webpage snapshots and petabytes of data.
Approach: They propose a public search system that supports multimodal searches across 10,015,993 federal government PDFs from the 2020 End of Term crawl.
Outcome: The proposed system supports multimodal searches across 10,015,993 federal government PDFs from the 2020 End of Term crawl (70,958,487 total PDF pages) significant compute cost for GovScape’s pre-processing pipeline for 10 million PDFs was approximately 1,500, equivalent to 47,000 PDF pages per dollar spent on compute.
Reinforcement Learning on Pre-Training Data (2026.acl-long)

Copied to clipboard

Challenge: Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach: They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome: Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.
Finding the Dominant Winning Ticket in Pre-Trained Language Models (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies on pre-trained language models show that they can fine-tune parameters but achieve good downstream performance.
Approach: They find that a dominant winning ticket takes up 0.05% of the parameters and is transferable across different tasks.
Outcome: The proposed model can achieve comparable performance with the full-parameter model, the authors show . the dominant winning ticket takes up 0.05% of the parameters, and the model is transferable across tasks, they show - the authors conclude .
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering (2025.findings-acl)

Copied to clipboard

Challenge: Existing prompt-based debiasing methods exhibit instability due to sensitivity to prompt changes . fine-tuning-based techniques incur substantial computational overhead and catastrophic forgetting .
Approach: They propose a debiasing framework that encodes fairness-related features into separable directions in the hidden activation space.
Outcome: The proposed framework performs inference-time debiasing without requiring retraining or prompt design . it detects bias signatures in activations and then computes debiased steering vectors . the proposed framework is available to download in the u.s.
ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation (2021.acl-demo)

Copied to clipboard

Challenge: Existing models for pre-training are not convenient for users to find and set them up.
Approach: They propose to extend ProphetNet into other domains and languages by pre-training models . they pre-train a cross-lingual generation model ProphetNet-Multi and a Chinese generation model .
Outcome: The proposed models achieve new state-of-the-art on 10 benchmarks.
Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios (2024.findings-acl)

Copied to clipboard

Challenge: chain-of-thought (CoT) prompting has been shown to be effective on complex reasoning tasks, but the naive greedy decoding used in CoT prompting causes the repetitiveness and local optimality.
Approach: They propose a generalizable ensemble-optimization method that uses a set of reasoning paths to prompt a language model one more time to determine the optimal answer.
Outcome: The proposed method can be generalized to almost all scenarios where the type of input questions and answer format of reasoning paths may be unknown.
FastSeq: Make Sequence Generation Faster (2021.acl-demo)

Copied to clipboard

Challenge: Transformer-based models have made tremendous impact in natural language generation, but inference speed is still a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process.
Approach: They propose an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O to accelerate sequence generation without loss of accuracy.
Outcome: The proposed framework can accelerate the sequence generation by 4x to 9x with a simple one-line code change for a set of widely used and diverse models.
GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)

Copied to clipboard

Challenge: Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models.
Approach: They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks.
Outcome: The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages.
RikiNet: Reading Wikipedia Pages for Natural Question Answering (2020.acl-main)

Copied to clipboard

Challenge: Using Wikipedia pages to answer open-domain questions remains challenging in natural language understanding.
Approach: They propose a model which reads Wikipedia pages for natural question answering . it uses a dynamic paragraph dual-attention reader and a cascaded answer predictor .
Outcome: The proposed model outperforms the human model on the Natural Questions dataset . it achieves 74.3 F1 and 57.9 F1 on long-answer and short-answer tasks .
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.
Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge.
Approach: They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage.
Outcome: The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold.
Half-S: Halving the Scale for Near-Lossless 4-Bit LLM Training (2026.findings-acl)

Copied to clipboard

Challenge: Existing 4-bit training pipelines rely on max-scaling, which causes representation collapse . despite this, there are limitations in the accuracy of 4-bit LLM training .
Approach: They propose a scaling strategy that uses half-scaling as a hardware-friendly default . they propose fp4 support that allows for a faster scaling of large language models .
Outcome: The proposed scaling strategy narrows the gap between theoretical optimum and BF16 while maintaining the efficiency benefits of 4-bit training.
Vector Calligrapher: Generating Scalable Vector Graphics via Structured Linguistic Supervision (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to generate SVG-based fonts struggle with semantic ambiguity and inefficiency . edward mcginley: generic text tokenizers fragment coordinate-dense SVG XML into excessively long sequences .
Approach: They propose a system that treats SVG generation as a conditional language modeling task . they propose linguistic supervision framework that decomposes typographic style into interpretable linguistic dimensions .
Outcome: The proposed system improves CLIP score by +23% while reducing geometric error by 48% and boosts generation efficiency by 18% Command-per-Token (C/T) ratio.
NeuronBlocks: Building Your NLP DNN Models Like Playing Lego (D19-3)

Copied to clipboard

Challenge: Deep Neural Networks (DNN) have been widely employed in industry to address various natural language processing tasks.
Approach: They propose an NLP toolkit that encapsulates neural network modules as building blocks to construct various DNN models with complex architecture.
Outcome: The proposed toolkit can build, train, and test various DNN models with complex architecture.
PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Quantization is a viable solution for pre-trained language models, but most existing methods are task-specific and require customized training and quantization with a large number of trainable parameters.
Approach: They propose a "quantize before fine-tuning" framework that allows for quantization with a large number of trainable parameters on each individual task.
Outcome: The proposed framework is compatible with quantization-aware training and post-training quantization and corrects quantization errors.
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for news headline generation focus on producing a single short sentence . et al., 2017; Gehrmann e.t., 2018; Zhong ee., 2019) focus on single-headline generation.
Approach: They propose a method to generate multiple headlines with keyphrases of user interests . they propose generating multiple keyphrase-relevant headlines using a transformer decoder .
Outcome: The proposed method achieves state-of-the-art in terms of quality and diversity.
Allies: Prompting Large Language Model with Beam Search (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to build LLMs with stacking are limited by their information coverage and low fault tolerance.
Approach: They propose a method that leverages large language models to iteratively generate new queries from an input query.
Outcome: The proposed method outperforms baselines on open-domain question answering benchmarks.
CodeM: Less Data Yields More Versatility via Ability Matrix (2024.findings-acl)

Copied to clipboard

Challenge: Recent efforts to train code large language models have been booming recently . however, this will incur significant costs in constructing data and training model considering the countless downstream scenarios.
Approach: They propose a data construction strategy which decouples code LLMs’ abilities into two dimensions and constructs a lightweight training corpus that only covers a subset of target scenarios.
Outcome: The proposed model can train a multilingual multitasking model using less data and training data.
Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space (2020.emnlp-main)

Copied to clipboard

Challenge: Existing data augmentation techniques for natural language processing tasks are difficult to design.
Approach: They propose a controllable rewriting based question data augmentation method for machine reading comprehension, question generation and question-answering natural language inference tasks.
Outcome: The proposed method generates high-quality, high-quality question data samples on machine reading comprehension, question generation, and question-answering natural language inference tasks.

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