Papers by Shikun Li

15 papers
Improving Knowledge Graph Completion with Generative Hard Negative Mining (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for knowledge graph completion (KGC) use generative methods with a self-information-enhanced training strategy to generate high-quality negatives.
Approach: They propose to leverage a sequence-to-sequence architecture to generate high-quality hard negatives from the same decoding distributions as the anchor.
Outcome: The proposed method produces high-quality negatives with good hardness and diversity on three KGC benchmarks.
LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Reinforcement learning with verifiable rewards (RLVR) is a key technique for enhancing LLMs’ reasoning abilities, yet its data inefficiency remains a major bottleneck.
Approach: They propose a gradient-alignment-based method which intelligently selects the learnable and representative training reasoning data for RLVR post-training.
Outcome: Experiments on five reasoning benchmarks show that the proposed method significantly reduces training data requirements while improving performance.
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback (2026.findings-acl)

Copied to clipboard

Challenge: Unlike chatbots, autonomous agents act directly on external environments, making tool invocation safety critical for reliable deployment.
Approach: They develop a benchmark for step-level tool invocation safety detection in LLM agents and a guardrail model that proactively detects unsafe tool invoking actions before execution using multi-task reinforcement learning.
Outcome: The proposed model reduces harmful tool invocations of ReAct-style agents by 65% on average and improves benign task completion by 10% under prompt injection attacks.
Data Selection for Multi-turn Dialogue Instruction Tuning (2026.findings-acl)

Copied to clipboard

Challenge: Instruction-tuned language models often use noisy multi-turn dialogue datasets with topic drift, repetitive chitchat, and mismatched answer formats across turns.
Approach: They propose a dialogue-level framework that scores whole conversations rather than isolated turns.
Outcome: The proposed framework outperforms strong single-turn selectors, dialogue-level LLM scorers and heuristic baselines on three multi-turn benchmarks and an in-domain Banking test set.
Instruction Data Selection via Answer Divergence (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for instruction tuning use data-centric methods, but they do not explicitly reflect what a particular base model is missing.
Approach: They propose a method for instruction tuning that uses geometric structure of multi-sample outputs to select instruction data.
Outcome: The proposed approach outperforms strong selectors on six benchmarks spanning reasoning, knowledge, and coding.
MPL: Multiple Programming Languages with Large Language Models for Information Extraction (2025.findings-acl)

Copied to clipboard

Challenge: Existing research focuses on Python for code-style simulation, overlooking the potential of other widely-used PLs during the supervised fine-tuning phase.
Approach: They propose a framework that incorporates programming languages into IE tasks . they introduce function-prompt with virtual running to simulate code-style inputs .
Outcome: The proposed framework exploits the potential of different programming languages during the supervised fine-tuning phase.
Graph Enhanced Dual Attention Network for Document-Level Relation Extraction (2020.coling-main)

Copied to clipboard

Challenge: Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relation facts.
Approach: They propose to characterize the interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA) . they also propose a simple yet effective regularizer based on the natural duality of the S2R and R2S attentions, whose weights are also supervised by the supporting evidence of relation instances during training.
Outcome: The proposed model achieves competitive performance on an existing large-scale dataset while the predictions can be interpretable and easily observed.
Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering over Knowledge Graphs (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to answer natural language questions on knowledge graphs (KGQA) use large-scale entity-related text corpus or knowledge graph embeddings as auxiliary information to facilitate answer selection.
Approach: They propose to integrate explicit textual information and implicit KG structural features of relation paths into a novel rotate-and-scale entity link prediction framework.
Outcome: The proposed method is superior to existing methods on three KGQA datasets and shows that it can be used to identify answer entities.
Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have significantly enhanced their performance in various natural language processing tasks.
Approach: They propose a robust and pluggable knowledge rewriter that is optimized for LLM generation by supporting the model's supportiveness.
Outcome: The proposed model can be used to rewrite knowledge in a supervised manner.
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Copied to clipboard

Challenge: Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach: They propose a modular open-source library to equip LLMs with external knowledge.
Outcome: The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.
Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning (2026.acl-long)

Copied to clipboard

Challenge: Existing models that ground retrieval on external evidence are limited in their ability to implement retrieval-augmented generation.
Approach: They propose a retrieval-augmented generation model that embeds retrieval control directly into generation.
Outcome: The proposed model surpasses strong RAG baselines and uses substantially fewer parameters.
Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data (P19-1)

Copied to clipboard

Challenge: Existing methods to perform relation extraction are feature-based or kernel-based, but the results of our study show that they can improve the performance of a baseline model with more than 10% absolute increase in F1-score.
Approach: They propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss.
Outcome: The proposed model outperforms the state-of-the-art models on ACE 2005 Chinese and English corpus and significantly improves the performance of a baseline model with more than 10% increase in F1-score.
A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)

Copied to clipboard

Challenge: Empirical natural language processing (NLP) systems involve interoperation among multiple components . a wealth of NLP toolkits exist ( 4), such as spaCy, DKPro, CoreNLP.
Approach: They propose a unified open-source framework that supports fast development of NLP workflows . framework includes processors for NLP tasks, visualization, and annotation .
Outcome: The framework offers processors for NLP tasks, visualization, and annotation, and is extensible . it is delivered through two modularized yet integratable open-source projects, Forte and Stave .
Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Existing approaches to incorporate bilingual dictionaries into Neural Machine Translation (NMT) models have been criticized for lack of integration of bilingual lexical information into the neural architecture.
Approach: They propose a neural architecture to incorporate bilingual dictionaries into Neural Machine Translation models by introducing three new components: Pointer, Disambiguator, and Copier.
Outcome: The proposed method achieves the following merits inherently compared with previous efforts: (1) Pointer leverages the semantic information from bilingual dictionaries, for the first time, to better locate source words whose translation in dictionary can potentially be used; (2) Disambiguator synthesizes contextual information from source view and target view, both of which contribute to distinguishing translation of a specific source word from multiple candidates in dicaries; (3) Copier systematically connects Pointer and Disambiguators based on a hierarchical
TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection (2022.emnlp-main)

Copied to clipboard

Challenge: Existing vision-and-language pre-training models suffer from long visual sequences . experimental results show that TRIPS gains a speedup of 40% over previous similar VLP models .
Approach: They propose an efficient vision-and-language pre-training model with text-relevant image patch selection, TRIPS, which reduces the visual sequence progressively with a text-guided patch-selection layer in the visual backbone for efficient training and inference.
Outcome: The proposed model can speed up training and inference by 40% over previous models.

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