Papers by Siyu Zhu

14 papers
Specializing Pre-trained Language Models for Better Relational Reasoning via Network Pruning (2022.findings-naacl)

Copied to clipboard

Challenge: Pretrained masked language models inherit a considerable amount of relational knowledge from the source corpora.
Approach: They propose to specialize pretrained masked language models into relational models from the perspective of network pruning.
Outcome: The proposed model can represent grounded commonsense relations at non-trivial sparsity while being generalizable . the proposed model improves on a wealth of NLP tasks, but we know little about how much knowledge it imparts .
Multi-turn Response Selection using Dialogue Dependency Relations (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for multi-turn response selection ignore the dependencies between the turns.
Approach: They propose a dialogue extraction algorithm to transform a dialog history into threads based on their dependency relations.
Outcome: The proposed model outperforms the state-of-the-art models on DSTC7 and DSTF8* with competitive results on UbuntuV2 .
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval (2022.naacl-main)

Copied to clipboard

Challenge: Existing text-image approaches use pre-trained vision-language representations for text retrieval . however, these models pose non-trivial memory requirements and substantial indexing time .
Approach: They propose a framework to compress large pre-trained dual-encoders for lightweight text-image retrieval.
Outcome: The proposed model performs better on Flickr30K and MSCOCO benchmarks than the original full model on mobile devices.
Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding (2026.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Models (LLMs) mainly address isolated tasks such as emotion analysis or stance detection.
Approach: They propose a large-scale model that combines large-level annotations with hyperbolic space to model human cognitive states.
Outcome: The proposed model outperforms baseline models on cognitive dimensions on single dimension tasks while retaining strong hierarchical structure.
LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

Copied to clipboard

Challenge: Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach: They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome: The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications.
Approach: They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases.
Outcome: The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency.
DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Existing datasets focus on sentence-level event extraction, but document-level EE is limited due to the lack of large-scale and practical training and evaluation datasets.
Approach: They propose a document-level event extraction dataset with 27,000+ events and 180,000+ arguments.
Outcome: The proposed dataset includes 27,000+ events, 180,000+ arguments and large-scale manual annotations, fine-grained argument types and application-oriented settings.
MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Copied to clipboard

Challenge: Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach: They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome: The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.
Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model (2023.emnlp-main)

Copied to clipboard

Challenge: Existing work evaluates faithfulness using models trained on related tasks or in-domain synthetic data.
Approach: They propose to do zero-shot faithfulness evaluation with a foundation language model.
Outcome: The proposed model outperforms ChatGPT on faithfulness and inconsistency detection with 24x fewer parameters and is competitive with existing models.
Pruning Pre-trained Language Models with Principled Importance and Self-regularization (2023.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models often contain a vast amount of parameters, posing nontrivial requirements for storage and computation.
Approach: They propose a pruning method where model prediction is regularized by the latest checkpoint with increasing sparsity throughout pruning.
Outcome: The proposed approach is effective at sparsity levels, and can be applied to natural language understanding, question answering, and data-to-text generation tasks.
T⋆: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning (2026.acl-short)

Copied to clipboard

Challenge: Autoregressive (AR) modeling via next-token prediction dominates scaling practice and deployed systems.
Approach: They propose a TraceRL-based curriculum for progressive block-size scaling in masked diffusion language models.
Outcome: The proposed curriculum outperforms direct large-block TraceRL on two SDAR scales and three benchmarks and retains block-size-specific non-monotone updates while improving accuracy.
Low-Rank Prune-And-Factorize for Language Model Compression (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to reduce parameter redundancy in pre-processed language models fail to retain satisfactory performance under moderate to high compression rates.
Approach: They propose to use network pruning to extract low-rank sparsity pattern desirable to matrix factorization.
Outcome: The proposed method has a superior compression-performance trade-off compared to existing methods.
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Copied to clipboard

Challenge: Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach: They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome: The proposed model achieves 49.04% accuracy across five model families.
Context Compression for Auto-regressive Transformers with Sentinel Tokens (2023.emnlp-main)

Copied to clipboard

Challenge: Existing Transformer-based LLMs have limited performance due to complexity of attention module . key-value cache is the major memory footprint and inference latency problem .
Approach: They propose a plug-and-play approach that incrementally compresses token activation into compact ones . they also profile the benefit of context compression on improving the system throughout .
Outcome: The proposed approach reduces memory footprint and inference latency by compressing tokens into compact ones.

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