Papers by Yanming Li

9 papers
EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics (2026.findings-acl)

Copied to clipboard

Challenge: Existing models operate on static molecular representations or rely on external tools for reasoning.
Approach: They propose a framework that reformulates species-level molecular dynamics as a symbolic temporal language modeling problem.
Outcome: The proposed model outperforms neural networks and language-based baselines on multiple temporal prediction tasks and generates plausible interpretations of reaction dynamics.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for embedding knowledge graphs implicitly memorize relation rules to infer missing links, but they are difficult to memorize due to the inherent deficiencies of such implicit memorization strategy.
Approach: They propose a vertical learning paradigm that allows to explicitly copy target information from related factual triples for more accurate prediction.
Outcome: The proposed model improves generalization ability and makes distant link prediction significantly easier.
Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing summarization benchmarks overlap in time with pre-training corpora and fine-tuning datasets.
Approach: They propose a temporal generalization benchmark that contains data samples from 2010 to 2022 to understand the temporal ability of abstractive summarization models.
Outcome: The proposed benchmark analyzes data samples from 2010 to 2022 to understand the temporal generalization ability of abstractive summarization models.
Open-World Attribute Mining for E-Commerce Products with Multimodal Self-Correction Instruction Tuning (2025.acl-long)

Copied to clipboard

Challenge: Current AM methods focus on extracting attributes from unimodal text, underutilizing multimodal data.
Approach: They propose a framework for multimodal self-correction instruction tuning to extract new attributes from images and text with Multimodal Large Language Models.
Outcome: The proposed framework outperforms state-of-the-art methods on two datasets.
HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to solve the data imbalance problem are limited in extremely imbalanced data.
Approach: They propose a hybrid approach which adapts general networks for head categories and few-shot techniques for tail categories.
Outcome: The proposed approach improves the performance of Single networks with diverse loss objectives on tail or entire categories.
Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification (2021.emnlp-main)

Copied to clipboard

Challenge: Existing scientific claim verification models have problems of error propagation among modules and lack of sharing valuable information among modules.
Approach: They propose an approach that jointly learns the modules for the three tasks with a machine reading comprehension framework by including claim information.
Outcome: The proposed approach outperforms existing models on the SciFact dataset on the three tasks of abstract retrieval, rationale selection and stance prediction.
BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents (2026.findings-acl)

Copied to clipboard

Challenge: Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use.
Approach: They propose a modular framework that provides a unified view of backdoor threats in LLM agents.
Outcome: The proposed framework provides a unified, agent-centric view of backdoor threats in LLM agents.
Feasible is Not Enough: Cost-Aware Optimal Tool-Chain Planning on Multi-Solution Tool Graphs (2026.findings-acl)

Copied to clipboard

Challenge: Existing tools and benchmarks often form tool learning (TL) as a single-solution setting . exploring large-scale TG is computationally expensive, especially under constrained context budgets.
Approach: They propose a framework for learning optimal TL policies over large tool graphs . they train a reinforcement learning agent to acquire transferable expansion skills .
Outcome: The proposed framework improves task success and solution optimality by 46.21% and 66.34% on multiSoTLBench.
Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)

Copied to clipboard

Challenge: Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions.
Approach: They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions.
Outcome: The proposed model outperforms state-of-the-art methods and shows its utility.

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