Challenge: Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety violations.
Approach: They propose a critique-augmented guardrail model that distills knowledge from high-capacity LLMs by generating structured critiques alongside safety labels.
Outcome: The proposed model outperforms existing guardrail models on multiple safety benchmarks and achieves the highest average F1 and AUPRC.

Similar Papers

MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors.
Approach: They propose a multilingual guardrail with reasoning for prompt classification that integrates culturally and linguistically nuanced variants and supervised fine-tuning.
Outcome: The proposed guardrail outperforms baselines across in-domain and out-of-domain languages by more than 15%.
Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent research shows that reasoning-based language models offer significant benefits for LLM safety and guardrail applications.
Approach: They conduct an analysis of reasoning-based guardrail models for content moderation . they find reasoning models exhibit strong sample efficiency and inference efficiency .
Outcome: The reasoning-based guardrail models show strong performance across domains . the models achieve competitive performance with significantly fewer training examples .
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment.
Approach: They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses.
Outcome: The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm.
Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings (2025.coling-industry)

Copied to clipboard

Challenge: Existing approaches to filter out inappropriate user prompts or system outputs have been successful, but using fine-tuned LLMs as guardrails introduces increased latency and higher maintenance costs.
Approach: They propose to fine-tune a lightweight architecture that reduces the model size from LlamaGuard’s 7 billion parameters to approximately 67 million parameters.
Outcome: Sentence-BERT reduces the model size from 7 billion parameters to approximately 67 million while maintaining comparable performance on the AEGIS safety benchmark.
CodeGuard: Improving LLM Guardrails in CS Education (2026.findings-eacl)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly embedded in Computer Science classrooms to automate code generation, feedback, and assessment.
Approach: They propose a guardrail framework for educational AI systems that can handle unsafe and irrelevant prompts.
Outcome: The proposed framework reduces potentially harmful or policy-violating code completions by 30-65% without degrading performance on legitimate educational tasks.
Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are widely deployed as zero-shot evaluators for answer grading, content moderation, and document ranking.
Approach: They propose a system that trains LLMs with adapters to denoise embeddings and refocus attention.
Outcome: The proposed model lifts adversarial accuracy from 5% to 95% a 90 percentage-point gain while reducing clean-data accuracy by just 8 percentage points.
XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety evaluations rely on binary labels, overlooking the nuanced risk these outputs pose.
Approach: They propose a framework to assess the severity of extremist content generated by Large Language Models (LLMs) it categorizes model responses into five danger levels (0–4) defined by degree of extremism endorsement .
Outcome: The proposed framework categorizes model responses into five danger levels (0–4) defined by degree of extremist endorsement, enabling nuanced analysis of failure frequency and severity.
LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing security guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility.
Approach: They propose a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities.
Outcome: The proposed framework significantly outperforms baseline guardrails on multiple real-world LLMs, achieving superior robustness, adaptability, and generalization.
Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks but are vulnerable to meticulously crafted jailbreak attacks.
Approach: They propose a training-free defense strategy to align LLMs’ strong safety discrimination performance with their relatively weaker safety generation ability.
Outcome: The proposed strategy achieves an average 99% success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks.
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router (2026.acl-long)

Copied to clipboard

Challenge: Current alignment approaches rely on refusal alignment to avoid harmful content . large language models are often overly cautious or overlook subtle harmful content.
Approach: They propose a framework for fine-grained safe generation in Large Language Models that enables real-time, token-level harmfulness detection and redaction without loss in capability.
Outcome: The proposed framework achieves over 90% in F1 score for detecting and redacting harmful content while preserving overall utility and informativeness of the model’s responses.

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