Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach: They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome: The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Similar Papers

SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations.
Approach: They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark.
Outcome: The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks.
Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Extensive benchmarks evaluate LLM safety relying heavily on general standards . no benchmark datasets exist to evaluate the user-specific safety of LLMs .
Approach: a new benchmark is designed to assess user-specific aspect of LLM safety . authors propose a simple remedy based on chain-of-thought to improve user-specified safety.
Outcome: a new benchmark assesses the user-specific aspect of LLM safety . the proposed solution improves user-specified safety by chain-of-thought .
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety (2025.emnlp-main)

Copied to clipboard

Challenge: Existing surveys focus on interpretation or safety, but safety and understanding are core motivations for interpretation research.
Approach: They propose a framework that connects interpretation methods, enhancements they inform, and tools that operationalize them.
Outcome: The proposed framework summarizes nearly 70 studies at their intersections and concludes with open challenges and future directions.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches fail to fully capture all risks in tool utilization, resulting in financial loss or privacy leaking.
Approach: They propose a framework to assess the safety of LLM tool utilization in a prospective manner, covering malicious user instructions and diverse practical toolsets.
Outcome: The proposed framework significantly enhances LLMs’ self-awareness, enabling a more safer and trustworthy tool utilization.
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study (2025.emnlp-main)

Copied to clipboard

Challenge: Existing safety evaluations rely on artificial images to evaluate vision-language models . a recent study found that memes are more effective at bypassing safety measures than synthetic or typographic images.
Approach: They propose a benchmark pairing meme images with harmful and benign instructions . they assess multiple VLMs across single and multi-turn interactions .
Outcome: The proposed benchmark pairs real meme images with harmful and benign instructions.
Dynamic Evaluation for Oversensitivity in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks rely on static datasets that degrade over time as models evolve, leading to data contamination and diminished evaluative power.
Approach: They construct a framework that generates model-specific challenging datasets and aggregates them across diverse LLM families.
Outcome: The framework captures emerging defensive patterns and aligns with each model’s unique behavior.
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety evaluations of large language models aggregate harms under generic categories such as "Identity Hate" a bilingual benchmark identifies a selective safety trap, where defense rates vary by up to 42% within the same model solely based on the target group.
Approach: They propose a bilingual adversarial benchmark to audit selective safety in large language models . defense rates vary by up to 42% within the same model solely based on target group .
Outcome: The proposed benchmark identifies a selective safety trap in large language models . defense rates vary by up to 42% within the same model solely based on the target group.
A Chinese Dataset for Evaluating the Safeguards in Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: a recent study has shown that large language models can produce harmful responses, exposing users to unexpected risks.
Approach: They propose a dataset for the safety evaluation of Chinese LLMs in Mandarin Chinese . they extend the dataset to better identify false negative and false positive examples .
Outcome: The proposed dataset is for the safety evaluation of Chinese LLMs, and is based on a Chinese dataset.
LongSafety: Evaluating Long-Context Safety of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating long sequences.
Approach: They propose a benchmark to evaluate LLM safety in open-ended long-context tasks . they find that relevant context and extended input sequences can exacerbate safety risks .
Outcome: The proposed benchmark identifies significant safety vulnerabilities in 16 LLMs . strong safety performance in short-context scenarios does not correlate with safety in long-contact tasks .
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) often refuse to answer legitimate queries, causing models to treat many reasonable prompts as potentially risky.
Approach: They propose a framework that automatically generates and selects overrefusal prompts near the safety boundary.
Outcome: The proposed framework identifies and curates boundary-aligned prompts, enabling more effective and targeted mitigation of overrefusal.

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