Papers by Jian Kang

10 papers
How Does Context Matter? On the Robustness of Event Detection with Context-Selective Mask Generalization (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing studies focus on improving the overall performance of an ED model, but few consider the robustness of an existing model.
Approach: They propose a new training mechanism that can effectively mine context-specific patterns for learning and robustify an ED model.
Outcome: The proposed model can learn a complementary predictive bias with most ED models that use full context for feature learning.
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning (2026.acl-long)

Copied to clipboard

Challenge: Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting.
Approach: They propose a framework that aligns replay schedules with a model-centric notion of time.
Outcome: Experiments on three benchmarks show that FOREVER consistently mitigates catastrophic forgetting.
Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift.
Approach: They propose a Meta-Cognitive Memory Abstraction method which decouples task execution from memory management by combining a frozen task model with a learned memory copilot.
Outcome: Experiments on ALFWorld, ScienceWorld, and BabyAI show that the proposed method improves performance, out-of-distribution generalization, and cross-task transfer over several baselines.
Event Extraction as Machine Reading Comprehension (2020.emnlp-main)

Copied to clipboard

Challenge: Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts.
Approach: They propose a new learning paradigm for event extraction by explicitly casting it as a machine reading comprehension problem.
Outcome: The proposed model achieves state-of-the-art performance on the data-scarce scenario, achieving 49.8% in F1 for event argument extraction with only 1% data, compared with 2.2% of the previous method.
Learning with Partial Annotations for Event Detection (2023.acl-long)

Copied to clipboard

Challenge: Event detection (ED) requires fully labeled and high-quality training data.
Approach: They propose a new trigger localization formulation using contrastive learning to distinguish ground-truth triggers from contexts and show a decent robustness for addressing partial annotation noise.
Outcome: The proposed approach achieves an F1 score of over 60% in an extreme scenario where 90% of events are unlabeled.
Graph-Based Knowledge Integration for Question Answering over Dialogue (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches for question answering over dialogue did not consider dialogue structure and background knowledge (e.g., relationships between speakers).
Approach: They propose a method which organizes a dialogue as a "relational graph" and uses edges to represent relationships between entities to encode multi-relations knowledge for reasoning.
Outcome: The proposed method is better at tackling complex questions requiring relational reasoning and defending adversarial attacks with distracting sentences.
LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing SEA-focused benchmarks miss Lao-specific cultural grounding and linguistic properties.
Approach: They propose a multi-dimensional benchmark for assessing large language models in Lao . they use open-source and held-out subsets to evaluate languages with a hybrid pipeline .
Outcome: LaoBench is the first large-scale, high-quality, and multidimensional benchmark for assessing LLM language understanding and reasoning in Lao.
Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are powerful automatic evaluators for natural language generation (NLG) tasks, but their uncertainty may limit their deployment in many applications.
Approach: They propose a conformal prediction framework that provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.
Outcome: The proposed framework provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs).
Approach: They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.
Outcome: The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters.
Neural Cross-Lingual Event Detection with Minimal Parallel Resources (D19-1)

Copied to clipboard

Challenge: Existing methods for event detection (ED) rely on high-performance machine translation systems or manually aligned documents to achieve a decent performance.
Approach: They propose a method that uses context-dependent translation to construct a lexical mapping between different languages and a shared syntactic order event detector for multilingual co-training.
Outcome: The proposed method performs cross-lingual transfer and tackles the extremely annotation-poor scenario.

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