Papers by Jun Hou

7 papers
Improving Event Detection via Open-domain Trigger Knowledge (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for event detecting are prone to overfitting densely labeled trigger words due to the small scale of training data.
Approach: They propose a novel Enrichment Knowledge Distillation model to leverage external open-domain trigger knowledge to reduce in-built biases to frequent trigger words in annotations.
Outcome: The proposed model outperforms nine strong baselines and is especially effective for unseen/sparsely labeled trigger words.
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Copied to clipboard

Challenge: Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach: They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome: Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact (2024.findings-acl)

Copied to clipboard

Challenge: Existing quantization methods are compromising performance of large language models (LLMs) despite their high computational intensity, LLMs are still demanding intensive computation.
Approach: They propose to generate the KV cache of pivot tokens losslessly from the full-precision model.
Outcome: The proposed method generates the KV cache of pivot tokens losslessly from the full-precision model with no extra inference overhead.
A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare (2025.findings-emnlp)

Copied to clipboard

Challenge: a survey of large language models in healthcare raises critical concerns around trustworthiness . trustworthy of LLMs in healthcare remains underexplored, lacking a systematic review .
Approach: a new survey examines the trustworthiness of large language models in healthcare . a review examines how each dimension affects reliability and ethical deployment of LLMs .
Outcome: The present study examines the trustworthiness of large language models in healthcare . it identifies key gaps in existing approaches and challenges posed by evolving paradigms .
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have focused on building dynamic benchmarks to address data contamination issues.
Approach: They propose a method for identifying shortcut neurons through comparative and causal analysis to suppress shortcut neurons.
Outcome: The proposed method overestimates contaminated models and is highly generalizable across benchmarks and hyperparameter settings.
BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for multimodal learning are difficult to scale beyond two modalities and lack resolution for instance-level control.
Approach: They propose a bi-level weighting framework that combines instance-level Kullback-Leibler divergence and modality-level mutual information to dynamically adjust modality importance during training.
Outcome: The proposed method significantly improves regression performance and multiclass classification accuracy.
Improving Entity Linking through Semantic Reinforced Entity Embeddings (2020.acl-main)

Copied to clipboard

Challenge: Existing entity embeddings are effective, but too distinctive for linking models to learn contextual commonality.
Approach: They propose a method to inject fine-grained semantic information into entity embeddings . they use word embedds of type words to generate semantic embeddngs based on existing embeddables a sample of semantic information is injected into the embedded entities .
Outcome: The proposed method reduces the distinctiveness of existing embeddings and improves performance.

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