Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications (2026.acl-long)
Copied to clipboard
| Challenge: | Existing safety evaluation paradigms rely on constructed benchmarks or dynamic red-teaming to probe potential vulnerabilities. |
| Approach: | They propose a framework that integrates specification-based software testing with AI safety. |
| Outcome: | The proposed framework achieves higher coverage and attack success counts compared to baselines. |
Similar Papers
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors (2024.findings-emnlp)
Copied to clipboard
Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
| Challenge: | Existing tools for detecting safety issues in LLMs are expensive and inefficient. |
| Approach: | They propose an LLM-based safety detector which annotates the safety of queries and provides explanations for its decisions. |
| Outcome: | The proposed detector outperforms baselines on four sets of query-response pairs and is effective as a safety evaluator for advanced LLMs. |
SAGE: A Generic Framework for LLM Safety Evaluation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Current safety evaluation methodologies focus on single-turn interactions with generic policies, failing to capture conversational dynamics of real-world usage and application-specific harms. |
| Approach: | They propose a framework for customized and dynamic harm evaluations that employs prompted adversarial agents with diverse personalities based on the Big Five model. |
| Outcome: | The proposed framework enables system-aware multi-turn conversations that adapt to target applications and harm policies. |
Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models for test case generation have improved branch coverage via prompt-engineered mutations, limiting their effectiveness for discovering subtle bugs and security vulnerabilities. |
| Approach: | They propose a program structure-aware LLM framework that integrates code property graphs and code semantics to condition test case generation on execution branches. |
| Outcome: | Experiments on real-world projects show that GLMTest improves branch accuracy from 27.4% to 50.2% on TestGenEval benchmark compared with state-of-the-art LLMs, i.e., Claude-Sonnet-4.5 and GPT-4o-mini. |
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs (2026.acl-long)
Copied to clipboard
Dasol Choi, DongGeon Lee, Brigitta Jesica Kartono, Helena Berndt, Taeyoun Kwon, Joonwon Jang, Haon Park, Hwanjo Yu, Minsuk Kahng
| Challenge: | Large language models are being rapidly adopted across a wide range of domains, including healthcare, finance, and the public sector. |
| Approach: | They propose a framework to evaluate whether large language models comply with policies . they apply COMPASS to eight diverse industry scenarios to validate models . |
| Outcome: | The proposed framework evaluates whether LLMs comply with allowlist and denylist policies. |
Beyond Superficial Tests: Adversarial Refinement for Reliable Property-Based Testing (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation, yet their application to Property-Based Testing (PBT) remains fraught with a superficiality gap. |
| Approach: | They propose an agentic framework that hardens software properties through Adversarial Refinement. |
| Outcome: | a new framework hardens software properties through Adversarial Refinement that detects and fixes bugs in top-tier libraries. |
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. |
The Structural Safety Generalization Problem (2025.findings-acl)
Copied to clipboard
Julius Broomfield, Tom Gibbs, George Ingebretsen, Ethan Kosak-Hine, Tia Nasir, Jason Zhang, Reihaneh Iranmanesh, Sara Pieri, Reihaneh Rabbany, Kellin Pelrine
| Challenge: | LLM jailbreaks are a widespread safety challenge. |
| Approach: | They propose a structure-rewriting guardrail that allows for more efficient safety assessment . single-turn attacks are the most extensively explored in the literature . |
| Outcome: | The proposed framework can be used to enable new defenses, the authors show . they show that the proposed framework reduces the risk of harmful inputs . |
Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing alignment methods focus on reactive feedback, where immediate human perception is leveraged to judge sampled model responses as preference data for post-training. |
| Approach: | They propose a proof-of-concept framework that projects how model-generated advice could propagate through societal systems on a macroscopic scale over time, enabling more robust alignment. |
| Outcome: | The proposed framework achieves 20% improvement on existing safety benchmarks and an average win rate exceeding 70% against strong baselines. |
Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis (2026.acl-demo)
Copied to clipboard
Cheng Wen, Hu Junjie, YiKun Hu, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Shengchao Qin, Cong Tian
| Challenge: | Formal verification typically requires developers to write detailed formal specifications . a formal verification system that generates candidate specifications is costly and error-prone . |
| Approach: | They propose an LLM-driven neuro-symbolic demonstration system that reframes specification writing as constrained structured synthesis. |
| Outcome: | The proposed system reduces hallucinations and produces proof-ready annotations. |
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Domain-specific datasets of harmful prompts are scarce and often rely on manual construction. Existing efforts to improve domain knowledge and reduce harmful prompt generation are lacking. |
| Approach: | They propose a framework that transforms domain knowledge into actionable constraints and increases the implicitness of generated harmful prompts. |
| Outcome: | The proposed framework yields high-quality datasets combining strong domain relevance with implicitness, enabling more realistic red-teaming and advancing LLM safety research. |