Human Feedback and Eval Paper Explorer

Match reason: Matches selected tags (Coding, Red Team).

• To enable systematic study, we unify and formalize safe, helpful, and pedagogical behaviors with a knowledge-mastery graph and introduce SHAPE, a benchmark of 9,087 student-question pairs for evaluating tutoring behavior under adversarial…
• Experiments across multiple LLMs show that our method yields significantly improved safety under two pedagogical jailbreak settings, while maintaining near-ceiling helpfulness under the same evaluation protocol.

Match reason: Matches selected tags (Coding, Red Team).

• Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols.
• We introduce JAILBREAK FOUNDRY (JBF), a system that addresses this gap via a multi-agent workflow to translate jailbreak papers into executable modules for immediate evaluation within a unified harness.

Match reason: Matches selected tags (Coding, Red Team).

• Large language model (LLM) safety evaluation is moving from content moderation to action security as modern systems gain persistent state, tool access, and autonomous control loops.
• We present AJAR, a red-teaming framework that exposes multi-turn jailbreak algorithms as callable MCP services and lets an Auditor Agent orchestrate them inside a tool-aware runtime built on Petri.

Match reason: Matches selected tags (Coding, Red Team).

• Experimental results reveal a harmful bias inherent in the standard greedy remasking strategy and identify a critical phenomenon we term Denoising-path Dependence, where the safety of early-stage tokens decisively influences the final…
• These findings also indicate that while current decoding strategies constitute a significant vulnerability, dLLMs possess a substantial intrinsic safety potential.

Match reason: Matches selected tags (Coding, Red Team).

• These models serve as suitable drop-in replacements for a broad range of safety-critical applications, where the risks of text-based manipulation outweigh the utility of text recognition.

Match reason: Matches selected tags (Coding, Red Team).

• Token-level jailbreak attacks often produce incoherent or unreadable inputs and exhibit poor transferability, while prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity.

Match reason: Matches selected tags (Coding, Red Team).

• Optimus integrates a training-free toxicity classification scheme that repurposes the safety alignment of commodity LLMs, and employs a dual-strategy alignment process combining synthetic "healing data" with Direct Preference Optimization…
• Extensive evaluations demonstrate that Optimus mitigates toxicity even when relying on extremely biased classifiers (with up to 85% degradation in Recall).

Match reason: Matches selected tags (Coding, Red Team).

• We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies…

Match reason: Matches selected tags (Coding, Red Team).

• Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied.
• We introduce Indic Jailbreak Robustness (IJR), a judge-free benchmark for adversarial safety across 12 Indic and South Asian languages (2.1 Billion speakers), covering 45216 prompts in JSON (contract-bound) and Free (naturalistic) tracks.

Match reason: Matches selected tags (Coding, Red Team).

• As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap.
• Boa employs a two-phase search strategy: (1) breadth-first sampling to identify easily accessible jailbreaks, followed by (2) depth-first priority search guided by fine-grained safety scores to systematically explore promising yet…

Match reason: Matches selected tags (Coding, Red Team).

• Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails.
• Rather than relying on curated safety-specific data or costly image-to-text conversion, we introduce a new formulation of the safety-relevant distributional shift induced by the visual modality.

Match reason: Matches selected tags (Coding, Red Team).

• Safety-aligned LLMs remain vulnerable to digital phenomena like textese that introduce non-canonical perturbations to words but preserve the phonetics.
• A mechanistic analysis reveals that phonetic perturbations fragment safety-critical tokens into benign sub-words, suppressing their attribution scores while preserving prompt interpretability -- causing safety mechanisms to fail despite…