Large Language Models in the Abuse Detection Pipeline

Suraj Kath, Sanket Badhe, Preet Shah, Ashwin Sampathkumar, Shivani Gupta · Mar 31, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 31, 2026, 11:42 PM

Recent

Extraction refreshed

Apr 13, 2026, 6:38 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.20

Abstract

Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static classifiers and labor-intensive labeling struggle to keep pace with evolving threat patterns and nuanced policy requirements. Large Language Models introduce new capabilities for contextual reasoning, policy interpretation, explanation generation, and cross-modal understanding, enabling them to support multiple stages of modern safety systems. This survey provides a lifecycle-oriented analysis of how LLMs are being integrated into the Abuse Detection Lifecycle (ADL), which we define across four stages: (I) Label \& Feature Generation, (II) Detection, (III) Review \& Appeals, and (IV) Auditing \& Governance. For each stage, we synthesize emerging research and industry practices, highlight architectural considerations for production deployment, and examine the strengths and limitations of LLM-driven approaches. We conclude by outlining key challenges including latency, cost-efficiency, determinism, adversarial robustness, and fairness and discuss future research directions needed to operationalize LLMs as reliable, accountable components of large-scale abuse-detection and governance systems.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

Extraction flags indicate low-signal or possible false-positive protocol mapping.
Extraction confidence is 0.20 (below strong-reference threshold).
No explicit evaluation mode was extracted from available metadata.

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior.

Reported Metrics

partial

Latency, Cost

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: We conclude by outlining key challenges including latency, cost-efficiency, determinism, adversarial robustness, and fairness and discuss future research directions needed to operationalize LLMs as reliable, accountable components of large-scale abuse-detection and governance systems.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior.

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes:
Agentic eval: None
Quality controls: Not reported
Confidence: 0.20
Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

latencycost

Research Brief

Deterministic synthesis

Large Language Models introduce new capabilities for contextual reasoning, policy interpretation, explanation generation, and cross-modal understanding, enabling them to support multiple stages of modern safety systems. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 6:38 AM · Grounded in abstract + metadata only

Key Takeaways

Large Language Models introduce new capabilities for contextual reasoning, policy interpretation, explanation generation, and cross-modal understanding, enabling them to support…

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (latency, cost).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

Large Language Models introduce new capabilities for contextual reasoning, policy interpretation, explanation generation, and cross-modal understanding, enabling them to support multiple stages of modern safety systems.

Why It Matters For Eval

Large Language Models introduce new capabilities for contextual reasoning, policy interpretation, explanation generation, and cross-modal understanding, enabling them to support multiple stages of modern safety systems.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Gap: Evaluation mode is explicit

No clear evaluation mode extracted.
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: latency, cost

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.CY)
Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
KV Cache Offloading for Context-Intensive Tasks
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
A GAN and LLM-Driven Data Augmentation Framework for Dynamic Linguistic Pattern Modeling in Chinese Sarcasm Detection
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (detection)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote