Papers by Fan Mo

10 papers
ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocations (2025.emnlp-main)

Copied to clipboard

Challenge: Current models exhibit notable vulnerabilities in maintaining safety during multi-step tool interactions and in indirect harm scenarios.
Approach: They propose a safety fine-tuning dataset to fine- tune LLMs into assistants . they propose to use synthesized trajectories and realistic, context-aware sample generation .
Outcome: The proposed model maintains safety in multi-step and indirect harm scenarios with little impact on helpfulness.
Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge .
Approach: They propose a framework that enables dynamic and continuous alignment of large language models with human preferences.
Outcome: The proposed framework improves safety and accuracy of a 7B model with human annotations.
LogicST: A Logical Self-Training Framework for Document-Level Relation Extraction with Incomplete Annotations (2024.emnlp-main)

Copied to clipboard

Challenge: Document-level relation extraction (DocRE) is difficult due to the vast number of entity pairs.
Approach: They propose a neural-logic self-training framework that iteratively resolves conflicts and constructs the minimal diagnostic set for updating models.
Outcome: The proposed framework outperforms existing methods on the document-level relation extraction (docRE) benchmark.
DESED: Dialogue-based Explanation for Sentence-level Event Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for sentence-level event detection depend on manual annotations or domain expertise to design sophisticated templates and rules.
Approach: They propose a dialogue-based explanation paradigm to enhance sentence semantics for event detection.
Outcome: The proposed method can be applied to two event detection datasets.
CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for relation extraction use noisy instances and poor quality training data.
Approach: They propose a sentence-level DSRE method that denies noisy samples from the wrong classification space on the feature space by enhancing the classification consensus between two discrepant classifiers.
Outcome: The proposed method outperforms existing methods on widely-used benchmarks and significantly outperformed existing methods.
KiPT: Knowledge-injected Prompt Tuning for Event Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing prompt-based methods may suffer from low precision because they lack event-related semantic knowledge.
Approach: They propose a Knowledge-injected Prompt Tuning model to improve prompt tuning . event detection aims to detect events from text by identifying and classifying event triggers .
Outcome: The proposed model outperforms baseline models in few-shot scenarios.
Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions.
Approach: They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency .
Outcome: The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo .
Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)

Copied to clipboard

Challenge: 3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency.
Approach: They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity.
Outcome: The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources.
Key Mention Pairs Guided Document-Level Relation Extraction (2022.coling-1)

Copied to clipboard

Challenge: Document-level Relation Extraction (DocRE) aims to identify the relations between entities in a given document.
Approach: They propose a document-level relation extraction model with two modules to model mention-level relations.
Outcome: The proposed model outperforms existing state-of-the-art models on two public DocRE datasets and outperformed existing models.
Boosting Document-Level Relation Extraction by Mining and Injecting Logical Rules (2022.emnlp-main)

Copied to clipboard

Challenge: Document-level relation extraction (DocRE) aims to extract relations of all entity pairs in document.
Approach: They propose a logic enhanced framework that boosts DocRE by mining and injecting logic rules.
Outcome: The proposed framework outperforms LogiRE on two benchmarks.

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