5 papers
Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection
Sihan Hou, Xinmeng Hou, Zhijun Zhang +5
Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external observations manipulate subsequ…
MetaCrit: A Critical Thinking Framework for Self-Regulated LLM Reasoning
Xinmeng Hou, Ziting Chang, Zhouquan Lu +5
Large language models (LLMs) fail on over one-third of multi-hop questions with counterfactual premises and remain vulnerable to adversarial prompts that trigger biased or factuall…
Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
Xinmeng Hou, Peiliang Gong, Bohao Qu +3
While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-im…
Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extraction
Xinmeng Hou, Lingyue Fu, Chenhao Meng +3
Aspect-Opinion Pair Extraction (AOPE) and Aspect Sentiment Triplet Extraction (ASTE) have drawn growing attention in NLP. However, most existing approaches extract aspects and opin…
Mitigating Biases to Embrace Diversity: A Comprehensive Annotation Benchmark for Toxic Language
Xinmeng Hou
This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and…