Papers by Sheng Fu

14 papers
IFlyEA: A Chinese Essay Assessment System with Automated Rating, Review Generation, and Recommendation (2021.acl-demo)

Copied to clipboard

Challenge: Automated Essay Assessment (AEA) aims to judge students’ writing proficiency in an automatic way.
Approach: They propose to use Chinese AEA system IFlyEssayAssess to evaluate essays written by native Chinese students from primary and junior schools.
Outcome: The proposed system provides application services for essay scoring, review generation, recommendation, and explainable analytical visualization.
Is Reference Necessary in the Evaluation of NLG Systems? When and Where? (2024.naacl-long)

Copied to clipboard

Challenge: Despite recent advances in reference-free metrics, it has not been well understood when and where they can be used as an alternative to reference-based metrics.
Approach: They propose to use reference-free metrics to evaluate NLG systems . they find they have a higher correlation with human judgment and greater sensitivity to deficiencies in language quality .
Outcome: The proposed metrics exhibit higher correlation with human judgment and greater sensitivity to deficiencies in language quality.
RepEval: Effective Text Evaluation with LLM Representation (2024.emnlp-main)

Copied to clipboard

Challenge: Traditional metrics for automatic text evaluation are tailored to specific tasks, while LLM-based evaluation metrics are costly.
Approach: They propose a metric that leverages projections of LLM representations for evaluation.
Outcome: The proposed metric exhibits higher correlation with human judgments than previous methods on 14 datasets.
“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns? (2026.acl-long)

Copied to clipboard

Challenge: Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor.
Approach: They propose a multimodal pun generation pipeline and a model to evaluate their understanding of puns.
Outcome: The proposed benchmark improves the understanding of multimodal puns by 16.5% in the F1 test.
Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model (2023.acl-long)

Copied to clipboard

Challenge: Existing unsupervised approaches for learning knowledge graphs require multiple modules and require entity information or relation type for training.
Approach: They propose a method that uses a unified pretrained language model to achieve fully unsupervised graph-text mutual conversion for the first time.
Outcome: The proposed method outperforms state-of-the-art methods for G2T and T2G tasks by fine-tuning only one pretrained model.
FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression (2025.findings-emnlp)

Copied to clipboard

Challenge: Current compression strategies, including token eviction and learned projections, often lead to biased representations and may require costly model retraining.
Approach: They propose a training-free KV cache compression framework that equalizes the contribution of all tokens to the compressed representation.
Outcome: The proposed framework ensures unbiased information retention in the KV cache.
When Truthful Representations Flip Under Deceptive Instructions? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) follow maliciously crafted instructions to generate deceptive responses, posing safety challenges.
Approach: They use Sparse Autoencoders to analyze LLM's internal representations to determine when and how they "flip" from truthful to deceptive under deceptively crafted instructions.
Outcome: The proposed model's True/False output is predictable across all conditions based on the model''s representation, and the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations.
ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning (2025.emnlp-demos)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in Machine Translation (MT) tasks.
Approach: They propose a translation agent system designed for multimodal input that leverages visual and contextual background information to enhance the translation process.
Outcome: The proposed translation agent achieves significantly higher translation quality in subtitle generation and general translation tasks compared to previous state-of-the-art systems.
BTS: Harmonizing Specialized Experts into a Generalist LLM (2025.emnlp-main)

Copied to clipboard

Challenge: Branch-Train-Stitch (BTS) is an efficient and flexible training algorithm for combining independently trained large language model (LLM) experts into a single, capable generalist model.
Approach: They propose an efficient and flexible training algorithm for combining large language model (LLM) experts into a single, capable generalist model using lightweight stitch layers.
Outcome: The proposed model can generalize to new domains despite being frozen . it yields the best generalist performance on a variety of downstream tasks, retaining the specialized capabilities of each of the experts.
Exploring and Verbalizing Academic Ideas by Concept Co-occurrence (2023.acl-long)

Copied to clipboard

Challenge: a new framework for academic idea inspiration is being developed for academic research assistants . number of academic publications is increasing exponentially, making it difficult for an independent researcher to understand these papers thoroughly.
Approach: They propose a framework based on concept co-occurrence for academic idea inspiration . they construct evolving concept graphs according to the co-existence relationship of concepts from 20 disciplines or topics .
Outcome: The proposed system can be used to explore connections between academic concepts and verbalize the new ideas.
Noisy-Labeled NER with Confidence Estimation (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies in deep learning have shown significant progress in named entity recognition (NER) . however, most existing works assume clean data annotation, while real-world data typically involve a large amount of noises.
Approach: They propose a confidence estimation approach for named entity recognition using noisy labels using local and global independence assumptions.
Outcome: The proposed method marginalizes out labels of low confidence with a CRF model and integrates it into a self-training framework for boosting performance.
JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for compression of Multimodal Large Language Models lack multimodal adaptation to preserve cross-modal synergy.
Approach: They propose a framework that aligns vision and language manifolds via a Joint Covariance basis and propose Global Spectrum-Aware Truncation to dynamically transfer parameter budget to the sensitive Backbone.
Outcome: Experiments on Qwen2.5-VL and Llama-3-Next confirm that JW-SVD retains both text and image capabilities.
Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Quantization enables efficient deployment of large language models in resource-constrained environments . but impact on truthfulness remains largely unexplored .
Approach: They propose a framework to assess the truthfulness of quantized large language models . they find quantized models retain internally truthful representations but produce false outputs .
Outcome: The framework assesses the truthfulness of quantized models across three dimensions . it finds that quantized model models retain internally truthful representations but are more susceptible to false outputs .
Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Copied to clipboard

Challenge: Open-ended Visual Question Answering (VQA) requires models to reason over visual and natural language inputs using world knowledge.
Approach: They propose a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time.
Outcome: The proposed pipeline expands the knowledge coverage from in-domain training data by 4.1% on OK-VQA, without additional computation cost.

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