A Lightweight LLM Framework for Disaster Humanitarian Information Classification

• URL: http://arxiv.org/abs/2602.12284v1
• Date: Wed, 21 Jan 2026 02:05:25 GMT
• Title: A Lightweight LLM Framework for Disaster Humanitarian Information Classification
• Authors: Han Jinzhen, Kim Jisung, Yang Jong Soo, Yun Hong Sik,
• Abstract summary: This paper develops a lightweight, cost-effective framework for disaster tweet classification using parameter-efficient fine-tuning.<n>We construct a unified experimental corpus by integrating and normalizing the HumAID dataset.<n>We demonstrate that LoRA achieves 79.62% humanitarian classification accuracy (+37.79% over zero-shot) while training only 2% of parameters.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Timely classification of humanitarian information from social media is critical for effective disaster response. However, deploying large language models (LLMs) for this task faces challenges in resource-constrained emergency settings. This paper develops a lightweight, cost-effective framework for disaster tweet classification using parameter-efficient fine-tuning. We construct a unified experimental corpus by integrating and normalizing the HumAID dataset (76,484 tweets across 19 disaster events) into a dual-task benchmark: humanitarian information categorization and event type identification. Through systematic evaluation of prompting strategies, LoRA fine-tuning, and retrieval-augmented generation (RAG) on Llama 3.1 8B, we demonstrate that: (1) LoRA achieves 79.62% humanitarian classification accuracy (+37.79% over zero-shot) while training only ~2% of parameters; (2) QLoRA enables efficient deployment with 99.4% of LoRA performance at 50% memory cost; (3) contrary to common assumptions, RAG strategies degrade fine-tuned model performance due to label noise from retrieved examples. These findings establish a practical, reproducible pipeline for building reliable crisis intelligence systems with limited computational resources.

Related papers

• Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA [50.97792275353563]
  We introduce a novel framework that restructures a single Low-Rank Adaptation (LoRA) module as a decomposable Rank-1 Expert Pool.<n>Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the [Guided] token.
  arXiv  Detail & Related papers  (2026-01-30T10:54:51Z)
• ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models [67.15960154375131]
  Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces.<n>This capability introduces a new class of prompt-induced inference-time denial-of-service (PI-DoS) attacks that exploit the high computational cost of reasoning.<n>We present ReasoningBomb, a reinforcement-learning-based PI-DoS framework that is guided by a constant-time surrogate reward.
  arXiv  Detail & Related papers  (2026-01-29T18:53:01Z)
• Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models [0.0]
  We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI.<n>We curate a dataset of 80,851 examples from 18 public cybersecurity sources and 35,026 synthetic OpenTelemetry traces.<n>Our custom benchmark accuracy improves from 42.86% to 74.29%, a statistically significant 31.4-point gain.
  arXiv  Detail & Related papers  (2025-12-29T09:41:22Z)
• A Domain-Adapted Pipeline for Structured Information Extraction from Police Incident Announcements on Social Media [11.463924147467297]
  We develop a domain-adapted extraction pipeline for structured information extraction from police incident announcements.<n>We use a high-quality, manually annotated dataset of 4,933 instances derived from 27,822 police briefing posts on Chinese Weibo.<n>We show that LoRA-based fine-tuning significantly improved performance over both the base and instruction-tuned models.
  arXiv  Detail & Related papers  (2025-12-18T05:08:26Z)
• Structured Uncertainty guided Clarification for LLM Agents [126.26213027785813]
  LLM agents extend large language models with tool-calling capabilities, but ambiguous user instructions often lead to incorrect invocations and task failures.<n>We introduce a principled formulation of structured uncertainty over tool-call parameters, modeling joint tool-argument clarification as a POMDP with Expected Value of Perfect Information (EVPI) objective for optimal question selection and aspect-based cost modeling to prevent redundancy.<n>Our SAGE-Agent leverages this structured uncertainty to achieve superior efficiency: increasing coverage on ambiguous tasks by 7-39% while reducing clarification questions by 1.5-2.7$times$ compared to strong prompting and uncertainty-based baselines.
  arXiv  Detail & Related papers  (2025-11-11T21:50:44Z)
• Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models [28.80331720382804]
  We introduce Orion, a training framework that enables compact models to perform iterative retrieval through learned search strategies.<n>Orion combines synthetic trajectory generation and supervised fine-tuning to encourage diverse exploration patterns in models.<n>Despite using only 3% of the training data available, our 1.2B model achieves 77.6% success on SciFact.
  arXiv  Detail & Related papers  (2025-11-10T19:49:55Z)
• Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People [81.63702981397408]
  Given limited resources, to what extent do agents based on language models (LMs) act rationally?<n>We develop methods to benchmark and enhance agentic information-seeking, drawing on insights from human behavior.<n>For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling)
  arXiv  Detail & Related papers  (2025-10-23T17:57:28Z)
• An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models [17.220143037047627]
  Advanced Persistent Threats (APTs) compromise high-value systems to steal data or disrupt operations.<n>Existing methods suffer from poor platform generality, limited generalization to evolving tactics, and an inability to produce analyst-ready reports.<n>We present an LLM-empowered attack investigation framework augmented with a dynamically adaptable Kill-Chain-aligned threat knowledge base.
  arXiv  Detail & Related papers  (2025-09-01T08:57:01Z)
• DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management [24.48064724587068]
  We introduce DisastIR, the first comprehensive Information Retrieval evaluation benchmark specifically tailored for disaster management.<n>DisastIR comprises 9,600 diverse user queries and more than 1.3 million labeled query-passage pairs, covering 48 distinct retrieval tasks.<n>Our evaluations of 30 state-of-the-art retrieval models demonstrate significant performance variances across tasks, with no single model excelling universally.
  arXiv  Detail & Related papers  (2025-05-20T20:11:00Z)
• Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape [52.98187034726091]
  We introduce Flat-LoRA, which aims to identify a low-rank adaptation situated in a flat region of the full parameter space.<n>We show that Flat-LoRA improves both in-domain and out-of-domain generalization.
  arXiv  Detail & Related papers  (2024-09-22T11:24:10Z)
• CrisisMatch: Semi-Supervised Few-Shot Learning for Fine-Grained Disaster Tweet Classification [51.58605842457186]
  We present a fine-grained disaster tweet classification model under the semi-supervised, few-shot learning setting. Our model, CrisisMatch, effectively classifies tweets into fine-grained classes of interest using few labeled data and large amounts of unlabeled data.
  arXiv  Detail & Related papers  (2023-10-23T07:01:09Z)
• DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bank [52.20298962359658]
  In crisis events, people often use social media platforms such as Twitter to disseminate information about the situation, warnings, advice, and support. fully-supervised approaches require annotating vast amounts of data and are impractical due to limited response time. Semi-supervised models can be biased, performing moderately well for certain classes while performing extremely poorly for others. We propose a simple but effective debiasing method, DeCrisisMB, that utilizes a Memory Bank to store and perform equal sampling for generated pseudo-labels from each class at each training.
  arXiv  Detail & Related papers  (2023-10-23T05:25:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.