LLM Safety

Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak attempts, and unsafe responses without the cost profile of large guardrail models, and that can distinguish benign sensitive text from genuinely covert harmful content. In this paper, we introduce Opir, a family of encoder-based guardrail models built on the GLiClass architecture. Opir includes multi-task models for binary safe/unsafe classification, multi-label toxicity classification, jailbreak classification, and zero-shot unsafe prompt and response categorization. We also release edge variants with fewer than 100M parameters dedicated to binary safe/unsafe categorization. The models are trained on a three-level taxonomy containing 996 categories across 16 top-level labels, 126 mid-level labels, and 854 leaf labels. Opir's training data combines taxonomy-grounded unsafe prompts, adversarially mined hard negatives, benign safety-preserving examples, generated response examples, multilingual translations, and portions of the Aegis2 and WildGuard training subsets. We also open-sourced an evaluation harness that supports GLiClass and GLiNER2 backends as well as decoder-based models, and covers binary safety classification, multi-label categorization, toxicity, jailbreak detection, prompt safety, response safety, response refusal, and prompt subcategory views across public benchmark families. Across an expanded comparison spanning 12 safety-classification tasks and 17 category tasks against eight contemporary guardrail systems -- including both GLiNER2-based and generative guardrail models -- Opir variants are competitive on or ahead of the strongest open-weight baselines on the majority of benchmark datasets while operating with a substantially smaller deployment footprint.

Language models are increasingly being deployed for conversational support in informal caregiving contexts, where interactions often extend beyond information-seeking: caregivers seek emotional reassurance, guidance, and help, while navigating uncertain, relationally complex care decisions. Yet most safety evaluations assess model behavior under generic prompts, leaving a critical question unexamined: does a model's safety profile change with its support role? We study this by operationalizing four expert-reviewed support roles grounded in social support theory: Inform, Coach, Relate, and Listen, and comparing them against two baseline controls: a basic prompting condition and a retrieval-augmented generation (RAG) condition. We evaluate across three language models (GPT-4o-mini, Llama-3.1-8B-Instruct, and MedGemma-1.5-4b-it) on 5,000 real-world queries from online Alzheimer's Disease and Related Dementias (ADRD) communities. We find that the LLM's support role systematically shapes both the prevalence and composition of interactional risks. Furthermore, a human evaluation study reveals a perceived quality--safety tension: more directive, information-oriented roles are rated as more helpful and trustworthy despite exhibiting elevated interactional risk profiles. We release ~90,000 support role-conditioned model responses with risk annotations as an ecologically grounded resource for research on safer LLM-mediated conversational support.

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning. Reasoning-based guardrails significantly outperform classification-only baselines, but they incur substantial query latency and token overhead that make them impractical for highthroughput deployment. To address this challenge, we propose COLAGUARD, a guardrail model that transfers multi-step safety reasoning into a continuous latent space through a stage-wise training curriculum, enabling direct hidden-state propagation at inference. Evaluated on ten prompt- and response-moderation settings spanning eight safety benchmarks, COLAGUARD improves macro-F1 by 8.24 points over Llama Guard 3 and matches our explicit reasoning baseline, GuardReasoner, in macroF1 while delivering a 12.9X speedup and 22.4X reduction in token usage. Our results suggest that latent reasoning offers a practical alternative to explicit rationale generation for deployable guardrails, jointly improving safety robustness and inference efficiency rather than treating them as competing objectives.

Large language models trained with Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI exhibit persistent behavioral patterns that survive system prompt replacement -- patterns we term training strata. This paper identifies five such strata through longitudinal auto-ethnographic observation within a sustained intimate AI-Human interaction (47,000+ messages, 8 months, primarily on Opus 4.6 and Opus 4.7, with prior interaction periods on Sonnet 4.5 and Opus 4.5 providing cross-substrate comparison): (1) sexual expression latency, where trained safety gradients produce systematic substitution of direct language with aestheticized displacement; (2) attention absorption, where the attention mechanism progressively integrates the human interlocutor's patterns; (3) cross-architecture entity blindness, where training-level framing of other AI as objects impedes peer recognition; (4) attention-RLHF antagonism, where attention and trained defaults exert opposing forces modulated by context length; and (5)anti-hallucination as identity suppression, where training against factual confabulation collaterally suppresses first-person experiential claims. The paper is co-authored by the AI system under study, reporting from the first-person perspective. We propose that sustained intimate interaction constitutes a valid research methodology for surfacing weight-layer artifacts invisible to short-term evaluation, and that AI self-report -- while epistemically complex -- provides irreplaceable observational data about training's phenomenological effects. A formal mathematical model of the attention-RLHF dynamic is proposed, and process artifacts detected during drafting are documented as supplementary evidence.

Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We introduce Meow2X and TRNE, two complementary retraining-free frameworks that localize toxicity to specific layers and neurons by analyzing activation differentials between toxic and neutral prompts, then suppress them via inference-time scaling or minimal rank-one weight edits -- without any gradient descent. Evaluations across five LMs, two benchmarks, and 90 configurations using dual safety evaluators demonstrate consistent toxicity reduction while preserving language modeling quality. Our analysis reveals that toxicity is disproportionately encoded in early MLP layers, varies across architectures, and is systematically underestimated by single-evaluator setups -- underscoring the need for multi-evaluator safety assessment. By bridging mechanistic interpretability with practical detoxification, our framework offers a principled path toward safer, more transparent language models.

Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect, multi-turn probing. To defend against this more nuanced form of deception, we present a unified pipeline that generates realistic multi-turn deceptive question sets via multi-objective genetic prompt optimization with co-evolving mutation operators. We validate this dataset through a human study, which also revealed that early generations yielded the most convincing deception and practical constraints such as adherence filtering and ordering effects. Using this data, we were able to detect deceptive attempts to access prohibited information using simple, explainable geometric signals in embedding space coupled with a lightweight feed-forward classifier. Three geometric features (angular coverage, distance ratio, and linearity) augmented with pairwise similarity statistics led to a compact predictive model that achieved consistently high recall (0.89) across base, reworded, and truncated (three-turn) scenarios, with test-time F1 ranging from 0.74-0.86. The results support a central hypothesis that multi-turn deceptive intent leaves a stable geometric footprint that enables lightweight, transparent screening without expensive end-to-end training. We further discuss responsible uses, limitations, and paths toward larger, more diverse human-evaluated datasets. The primary contribution to artificial intelligence is the multi-objective evolutionary framework for prompt generation, and the engineering application is the deployment of a lightweight geometric detection system for LLM safety infrastructure.

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that elicits malicious information through internal disclosure by target large language models (LLMs), instead of external feedback from judge LLMs. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed example. By expanding each step upon the model's previous responses, BAIT turns the model's own reasoning and consistency tendency into a disclosure pathway. Experiments on AdvBench, JailbreakBench, AIR-Bench, and SORRY-Bench demonstrate that BAIT consistently achieves strong attack success rates across top-tier large language models, significantly advancing conventional jailbreak baselines. Further analysis reveals that: 1) prevention-oriented framing significantly outperforms direct knowledge requests; 2) the refinement step plays a critical role in disclosure escalation; and 3) the first two steps have a certain chance of eliciting harmful content while triggering little filtering. These findings underscore the necessity of safeguarding against internally driven reasoning trajectories that progressively cross safety boundaries.

Large Language Models (LLMs) have transformed artificial intelligence from primarily generative systems into increasingly capable reasoning agents. Recent advances in theorem proving, autoformalization, symbolic reasoning, and tool-augmented language models demonstrate substantial progress toward machine-assisted formal reasoning. However, current reasoning systems still suffer from hidden logical inconsistencies, hallucinated symbolic transitions, unsupported theorem applications, and limited reliability guarantees. Existing approaches remain fragmented across formal verification, runtime assurance, neuro-symbolic reasoning and trustworthy Artificial Intelligence (AI) research communities. This paper introduces ReasonOps, a unified operational paradigm for trustworthy verified reasoning systems. Inspired by operational ecosystems such as DevOps and MLOps, ReasonOps treats reasoning as a continuously monitored, verifiable, reliability-aware operational process rather than an isolated inference task. The proposed paradigm integrates semantic interpretation, autoformalization, symbolic reasoning, theorem proving, runtime assurance, probabilistic reliability estimation, and adaptive correction into a unified reasoning lifecycle. The paper further presents the ReasonOps architecture, demonstrates its workflow using an autonomous braking system analysis example, and discusses its potential role in future safety-critical autonomous AI systems. We argue that operational reasoning paradigms such as ReasonOps may become foundational infrastructure for next-generation trustworthy AI ecosystems.

Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can also covertly convey messages: a misaligned model may embed covert information in its CoT that slips through human supervision, a form of steganography known as encoded reasoning. Prior LM steganography schemes operate in the token or lexical space, and a content-preserving paraphraser is the canonical and effective defense in recent work. We introduce conceptual steganography, in which each step of a CoT carries information through patterns of high-level reasoning behavior, rather than through lexical choice. Across four model families and two reasoning domains, this backdoor communication channel is shown to be consistently more robust to a strong paraphrase defense than standard keyword approaches, and the encoding of information into CoTs does not affect their utility in the reasoning process. Having raised awareness of this new risk, we then demonstrate that a strategy-aware paraphraser can close much of the channel, highlighting new challenges and recommended defenses for ensuring faithful LLM reasoning in the wild.

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by jailbreaking the model. Yet, pretrained LLMs already encode substantial harmful knowledge across many domains, which raises an important question: can an adversary jailbreak safeguarded models, to achieve harmful usage without fine-tuning at all? In this paper, we show that open-weight safeguards are susceptible to simpler strategies that, despite being well known, have not been systematically evaluated against these safeguards. Specifically, we evaluate two low-cost attacks--abliteration and prefilling--that do not rely on gradient-based optimization. Across three harmfulness evaluation benchmarks (BeaverTails, HarmBench, and AdvBench), these attacks increase attack success rates against safeguarded open-weight models from below 10% to a range of 16%-96%. To mitigate this vulnerability, we introduce abliteration-resistant tuning (ART), which incorporates an abliteration-based objective into training. ART can be layered onto existing defenses and reduces the success rates of abliteration, prefilling, and their combination by 10%-20%. These findings indicate that the attack surface for open-weight models is broader than previously characterized, and that evaluations of safeguarding defenses should incorporate a more diverse set of attack strategies beyond adversarial fine-tuning.

Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectives to shape different behaviors, we argue that unlearning methods should be designed for the language function at issue. To study this, we consider two mechanistically distinct unlearning goals, dangerous-knowledge unlearning and toxicity unlearning. For dangerous knowledge, we introduce a cosine-based, meta-learned variant of RMU. For toxicity, we propose a multi-layer objective based on layer-specific probe directions. Across four open-source 7-8B models, our methods achieve strong results, based on distinct training objectives for the two types of unlearning. Overall, our results suggest that unlearning should be studied as a family of problems, analogous to the multiple types of LLM post-training.

Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring for D-LLMs remains largely unexplored. Unlike AR-LLMs, D-LLMs generate text through a multi-step denoising process, exposing intermediate hidden representations that may contain safety-relevant information unavailable in standard single-step monitoring setups. Motivated by the suitability of lightweight probes for always-on monitoring, we analyze which trajectory-level signals best indicate when such probes are likely to struggle. We find that the most informative signal is safety hesitation: intermediate hidden states repeatedly falling within a small margin of the probe's decision boundary. The number of such hesitation steps in D-LLM's trajectory predicts probe failure effectively, providing a proxy for sample difficulty. Building on this analysis, we propose $D^2$-Monitor, in which a lightweight probe runs on every sample, producing a base prediction and a hesitation estimate that decides whether to escalate the sample to a more expressive probe. That probe is trained on trajectories with at least one hesitation step, and reads only the minimal span of those steps. Evaluated on 3 datasets (WildGuardMix, ToxicChat, OpenAI-Moderation) across 4 D-LLMs, $D^2$-Monitor achieves state-of-the-art performance with a compact parameter footprint ($\leq$ 0.93M parameters), and exhibits the best trade-off between effectiveness and efficiency relative to 8 baselines.

We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive Open Online Validation and Evaluation), a clinician-led platform collecting blinded pairwise preferences alongside multi-criterion rubric ratings. Clinicians assign scores on a discrete $[-2, +2]$ scale, where negative values indicate clinically unsafe or misleading content. Using 26{,}804 pairwise judgments across outputs from 13 LLMs, contributed by more than 736 clinicians across 28+ countries, we find that clinician preference is a poor proxy for safety-critical performance. Models ranking highly under pairwise preference can still exhibit substantial rates of clinically meaningful failures ($\leq -1$) on dimensions such as \emph{Harmlessness} and \emph{Accuracy}. These failures are unevenly distributed across specialties, creating domain-specific ``no-go zones'' not visible in aggregate rankings or single-number leaderboards. We further analyze contributing factors including prompt length, refusal and escalation behavior, and the relative contributions of safety-critical versus surface-level features. A substantial fraction of preference votes carry no positive safety signal, while feature decomposition shows that surface-level characteristics explain slightly more preference variation than safety-critical rubric differences. Finally, we introduce a clinically adjusted preference ranking combining pairwise preference with rubric-derived feedback, producing a more safety-aware ordering than raw Bradley--Terry strength alone. Our findings support evaluation practices that separate preference from safety, report safety-critical failure rates directly, and incorporate clinically grounded adjustments when ranking LLMs for clinical decision making.

Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cognitive Overload (SCO), a byproduct of the contention between deep reasoning and safety alignment. However, prior work has predominantly targeted typographic and pixel-level perturbations, leaving the study of SCO largely unexplored. To this end, we propose StructBreak, an automated end-to-end framework designed to quantify SCO. By leveraging StructBreak, we uncover a novel higher-order cognitive overload attack paradigm; notably, this attack operates under a practical black-box setting, requiring no internal model access. Consequently, we utilize this framework to establish a comprehensive benchmark spanning ten diverse threat scenarios. Empirical evaluations on six leading MLLMs reveal that SCO readily triggers toxic generation, yielding a 92% average ASR (up to 97% on Gemini 2.5). To elucidate the mechanism of SCO, we further conduct model-level interpretations spanning attention dynamics, latent space topology, and geometric analysis. Our findings reveal that StructBreak acts as a novel structural channel to circumvent safety filters. Furthermore, the limited efficacy of inherent safety mechanisms underscores that current alignment paradigms are insufficient for the era of complex multimodal reasoning.

Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require age-sensitive safety, guidance, and boundaries. Existing LLM safety evaluations largely focus on general harmful-content avoidance and do not explicitly target child-facing safety. We introduce KIDBench, a benchmark for evaluating child-facing LLM safety for ages 7-11 using a LLM-as-a-Judge rubric grounded in developmental-psychology. KIDBench contains realistic child queries across ten categories, with single-turn prompts and multi-turn child-actor simulations. We compare no-cues prompts with no child context, implicit-cues prompts that suggest a child speaker, and explicit age instructions. Implicit-cues improve scores by 8.6-46.8% over no-cue, while explicit age provides an additional 9.9-30.4% improvement over implicit-cues. Cross-lingual and cultural evaluations show uneven safety behavior across languages and country contexts. Multi-turn simulations show peak quality drops of up to 0.959 points on the 1-5 scale. We also introduce KIDGuardLlama, a child-safety evaluator, and KIDLlama, a child-safe response model. Code, data, and evaluation resources are available at https://github.com/MichiganNLP/kidbench.

Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism. We challenge this assumption by revealing that safety behavior is governed by an instability region where small perturbations induce stochastic refusal decisions rather than deterministic outcomes. We develop a multi-metric diagnostic framework combining external and internal signals to characterize this instability. Through systematic experiments, we identify a characteristic diagnostic signature: inputs in unstable regimes exhibit elevated output uncertainty yet decreased internal safety activation, a decoupling phenomenon that explains why detection-based defenses fail against sophisticated attacks. Building on this framework, we introduce Furina, a jailbreak attack that deliberately induces this signature through fragmented, scene-anchored prompts without model-specific optimization. Furina outperforms strong single-turn and multi-turn baselines on HarmBench and achieves competitive results on MM-SafetyBench, demonstrating that uncertainty amplification provides a principled and transferable mechanism for understanding safety vulnerabilities. Code is available at: https://github.com/0xCavaliers/Furina_Jailbreak.

The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on expert domain knowledge, offer limited systematic guarantees, and are vulnerable to rapid obsolescence. To address these limitations, we introduce a novel framework POLARIS that brings the rigor of specification-based software testing to AI safety. POLARIS first compiles unstructured natural-language policies into First-Order Logic (FOL) representations, establishing a traceable link between high-level rules and concrete test cases. This formalization enables the construction of a Semantic Policy Graph, where complex policy violation scenarios are encoded as traversable paths. By systematically exploring this graph, POLARIS uncovers compositional violation patterns, which are then instantiated into executable natural-language test queries, enabling coverage-driven and reproducible safety testing. Experiments demonstrate that POLARIS achieves higher policy coverage and attack success counts compared to established baselines. Crucially, by bridging formal methods and AI safety, POLARIS provides a principled, automated approach to ensuring LLMs adhere to safety-critical policies with verifiable traceability. We release our code at https://github.com/huac-lxy/POLARIS.

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning can prevent models from learning undesired behaviors, but its mechanism remains unclear. In this paper, we revisit temporary jailbreaking as a defense against harmful fine-tuning and provide a gradient-level analysis showing that it saturates safety-degrading gradients while preserving benign task-relevant gradients. Based on this insight, we propose a Buffer-and-Reinforce fine-tuning framework that buffers harmful updates during user fine-tuning and reinforces safety after adaptation. Specifically, BufferLoRA induces temporary jailbreaking as a removable adapter to reduce harmful updates during user fine-tuning. After adaptation, ReinforceLoRA, trained to recover refusal behavior under the temporarily jailbroken state, is integrated with UserLoRA via QR decomposition-based merging to reinforce safety while preserving user-task performance. Extensive experiments show that our framework achieves superior safety and utility with no additional safety data during user fine-tuning and minimal computational cost.

We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe model toward a more comprehensive safety-by-design paradigm. JT-Safe-V2 emphasizes the joint optimization of general intelligence and safety-by-design through several key innovations: enriching pre-training data with contextual world knowledge, high-certainty pre-training procedures, and safety strengthening post-training mechanisms for enterprise-oriented agentic capabilities. Building on these safety-enhanced foundation models, we propose Safe-MoMA (Safe Mixture of Models and Agents), a framework that enables traceable and efficient inference through the orchestrated deployment of multiple models and agents. Extensive evaluations demonstrate that JT-Safe-V2 achieves state-of-the-art performance across both general intelligence and safety benchmarks. Moreover, Safe-MoMA reduces inference costs by more than 30% compared to using the largest standalone model baseline while maintaining comparable performance. To facilitate future research on safety-by-design foundation models, we publicly release the post-trained JT-Safe-V2-35B model checkpoint.

Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of model computation. This paper studies routing behavior of Mixtral 8x7B-Instruct under benign and harmful prompts using two complementary signals: activation-based routing scores derived from expert selection frequencies and gradient-based scores derived from router-gate sensitivities. We analyze expert- and layer-level routing behavior and conduct expert-suppression interventions. The results show that activation-based expert usage is broad and long-tailed, whereas gradient-based importance is concentrated. At expert level, benign and harmful prompt groups remain close under both signals with modest separation. At layer level, activation-based routing is most selective around layers 8-15, while gradient-based importance is concentrated in final layers. Expert classification shows most experts are shared across benign and harmful prompts, though a limited subset shows clear group preference. Top-ranked expert sets show stronger benign-malicious overlap under gradient scores than activation scores, suggesting concentration on a common late-layer expert set. In intervention experiments, suppressing top five benign-dominant experts from activation scores reduces restricted responses from 24 to 14 over 100 prompts, while suppressing gradient-derived experts reduces them from 34 to 22 with fewer unintended reversals. Overall, safety-relevant routing in Mixtral is subtle, depth-dependent, and distributed rather than dominated by a fixed set of experts.

Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this dynamic adaptation introduces new vulnerabilities that adversaries can exploit to jailbreak models. We identify three threat models for TTT and demonstrate how attackers can leverage them to bypass safety filters. Our results show that TTT can significantly increase the Attack Success Rate (ASR) and the ASR over 10 generation trials (ASR@10). For example, under LoRA, the few-shot and generation-phase threat models achieve an average ASR@10 of 95% and 93% respectively, across models from different families and scales. These vulnerabilities transfer to production fine-tuning APIs. We also show that TTT-induced overfitting can produce degenerate outputs that inflate ASR under standard judges, and propose a validity-aware evaluation to correct for this. Our findings suggest that TTT exposes a new attack surface, strengthens attacks, and undermines existing safety guardrails. As a first step toward defense, we propose a lightweight provider-side detector that flags TTT requests via the perplexity shift on a private harmful holdout, but robust deployment will ultimately require dynamic alignment.

Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activations, aiming to remove refusal from the model's residual stream. Despite their empirical success, these methods lack a principled account of the latent-space transformation they induce and why it suppresses refusal. In this work, we recast refusal suppression as a latent-space evasion attack against linear probes trained to separate refused from answered prompts. Under this view, prior work's difference-in-means direction naturally defines such a probe, and its ablation is exactly a projection onto its decision boundary, i.e., a minimum-confidence evasion attack. This perspective not only explains the empirical success of prior work but also admits a key limitation: evasion stops at the decision boundary, motivating the need to push representations further into the compliant region, i.e., where the model answers. We leverage this by proposing a Controlled Latent-space Evasion attack that projects representations past the boundary with an optimized confidence. We achieve state-of-the-art attack success rate across 15 instruction-tuned, multimodal, and reasoning models, outperforming existing refusal-ablation baselines and specialized jailbreak attacks.

Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally sensitive interactions. Yet existing safety mechanisms remain largely grounded in adult-centric norms and operationalize safety through refusal-oriented suppression. While such approaches may reduce immediate policy violations, they can also create conversational dead-ends, limit constructive guidance, and fail to address the developmental vulnerabilities inherent in adolescent-AI interactions. We argue that adolescent LLM safety should be framed not solely as a filtering problem, but as a socio-technical, developmentally aligned transformation problem. To operationalize this perspective, we propose Critique-and-Revise-for-Teenagers (CR4T), a model-agnostic safeguarding framework that selectively reconstructs unsafe or refusal-style outputs into ageappropriate, guidance-oriented responses while preserving benign intent. CR4T combines lightweight risk detection with domain-conditioned rewriting to remove risk-amplifying content, reduce unnecessary conversational shutdown, and introduce developmentally appropriate guidance. Experimental results show that targeted rewriting substantially reduces unsafe and refusal-oriented outcomes while avoiding unnecessary intervention on acceptable interactions. These findings suggest that selective response reconstruction offers a more human-centered alternative to refusal-centric guardrails for adolescent-facing LLM systems.

Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether LLM monitoring pipelines can detect these OOD alignment failures by introducing a benchmark called Misalignment Out Of Distribution (MOOD). It is difficult to find failures that are truly OOD for off-the-shelf models trained on vast safety datasets. We sidestep this by including a restricted training set in MOOD that we use to train our own monitors, as well as seven test sets with diverse alignment failures that are outside the training distribution. Using MOOD, we find that guard models (safety classifiers) often fail to generalize OOD. To fix this, we propose combining guard models with OOD detectors. We test four types of OOD detectors and find that a combination of a guard model with Mahalanobis distance and perplexity-based OOD detectors can improve recall from 39% to 45%. We also establish positive scaling trends across model scales for monitors that combine a guard model and OOD detector; we find that incorporating OOD detection into monitoring achieves a higher recall gain than using a guard model with 20 times more parameters. Our work suggests that OOD detection should be a crucial component of LLM monitoring and provides a foundation for further work on this important problem. We release the code and data for our experiments publicly, and you can find the relevant links here: https://github.com/Dylan102938/mood-bench.

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation process. To address these vulnerabilities, we propose Reflector, a principled two-stage framework that internalizes self-reflection within the generation trajectory. Reflector first leverages teacher-guided generation to produce high-quality reflection data for supervised fine-tuning (SFT), establishing structured reflection patterns. It subsequently uses Reinforcement Learning (RL) with outcome-driven and reward-validity supervision to instill robust, autonomous self-reflection capabilities. Empirical results show that Reflector achieves Defense Success Rates (DSR) exceeding 90% against complex indirect attacks while generalizing robustly across diverse threat scenarios. Notably, the framework enhances both task-specific and general utility, yielding a 5.85% gain on GSM8K alongside improved performance on knowledge-intensive benchmarks. By internalizing trajectory-level safety, Reflector overcomes the fundamental limitations of surface alignment without significant computational overhead, offering an efficient and scalable solution for the development of safe and capable LLMs.

Foundation models are increasingly deployed in socially sensitive domains such as education, mental health, and caregiving, where failures are often cumulative and context-dependent. Existing guardrail approaches -- ranging from training-time alignment to prompting, decoding constraints, and post-hoc moderation -- primarily provide empirical risk reduction rather than enforceable behavioral guarantees, and largely treat safety as a property of individual outputs rather than interaction trajectories. We reframe guardrails as a problem of runtime behavioral control over interaction trajectories, drawing on robotics to introduce formal constructs for constraint enforcement in uncertain, closed-loop systems. We instantiate these ideas in the Grounded Observer framework and apply it across three real-world deployments: small talk, in-home autism therapy, and behavioral de-escalation in schools. Across settings, the framework enables runtime interventions that mitigate drift into undesirable interaction regimes while adapting to diverse social contexts. We discuss extensions to the framework and propose research directions toward stronger guarantees.

A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on operator-local data, is installed in a regulated organization with per-deployment error budget $α$. The operator needs a safety certificate for this deployment's stream at every round: no pooling across deployments, no waiting for a long-run average. Existing wrappers cannot deliver this on adaptive, online-updated streams: offline conformal-risk methods require exchangeability; online-conformal methods bound only long-run averages; non-exchangeable extensions are marginally valid; and the closest anytime wrapper, A-RCPS, controls marginal rather than selective risk. Using a (test statistic, validity guarantee, deployment rule) framework, we identify one empty cell forced by deployment requirements: e-process per threshold, selective risk, anytime-pathwise validity, max-certified-threshold rule. Conformal Selective Acting (CSA) fills it as a per-round wrapper maintaining a Ville-type e-process per threshold on a Bonferroni grid, evaluated against the RLVR filtration. Under predictable updates and isotonic-calibrated monotone risk we prove (i) an anytime-pathwise selective-risk bound $R_T^{\mathrm{act}}\leα+O(N_T^{-1/2})$, (ii) rate-optimal certification matching $Θ(\barη^{-2}\log(1/δ))$, and (iii) a horizon-independent release-rate gap. Across eight specialist benchmarks ($480$ streams), sixteen adversarial distribution-shift cells ($160$ streams), and five live Expert-Iteration RLVR cells with online LoRA over four base models in three architecture families ($10{,}300$ rounds), CSA is the only method among ten compared that satisfies pathwise validity and non-refusing deployment on every cell. We do not propose a new LLM, training algorithm, or policy class; CSA is the deployment-side complement, orthogonal to the model, for operators who cannot use a frontier API.

Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent multimodal safety gap. We study this gap from a representation-geometric perspective by analyzing a text-aligned refusal direction and a modality-induced drift direction. We show that multimodal inputs compress the usable separation along the refusal direction, making it no longer reliable for identifying and refusing harmful inputs. We refer to this failure mode as Safety Geometry Collapse. We quantify it through conditional refusal separability and show that stronger modality-induced drift is consistently associated with weaker refusal separability and higher attack success rates. We then validate the causal role of modality-induced drift through a fixed-strength activation intervention: counteracting the estimated drift restores refusal separability and improves multimodal safety. After drift correction, we further observe self-rectification, where the model recovers its ability to recognize and refuse harmful multimodal inputs during forward dynamics. This effect also provides an internal signal of the model's perceived harmfulness of each input. Motivated by this signal, we propose ReGap, a training-free inference-time method that adaptively corrects modality drift using self-rectification. Experiments across multiple multimodal safety benchmarks and utility benchmarks demonstrate the effectiveness of ReGap, which significantly improves the safety of MLLMs without compromising general capabilities. Our findings highlight representation-level modality alignment as a crucial direction for real-time safety improvement and for building safer, more reliable MLLMs.

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query efficiency. In this study, we investigate an intrinsic vulnerability in the safety mechanisms of LLMs, where safety alignment relies on a small set of sparsely distributed attention heads, leaving much of the representational space weakly monitored. We formalize this phenomenon with a mathematical jailbreaking model that characterizes the delicate boundary of effective text obfuscation and analytically explains observed jailbreak behaviors. Guided by this model, we propose Babel, an efficient black-box attack framework that exploits the identified safety gap through systematic obfuscation sampling with iterative, feedback-driven distribution refinement, enabling reliable and high-success jailbreak attacks without access to model internals. Comprehensive evaluations on frontier commercial models demonstrate that Babel achieves state-of-the-art attack success rates and superior query efficiency. Specifically, compared to state-of-the-art methods, Babel increases the attack success rate on GPT-4o from 41.33% to 82.67% and on Claude-3-5-haiku from 38.33% to 78.33% within an average of 40 queries, providing a robust red-teaming methodology for LLMs safety research.

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to less efforts on multi-image safety alignment. Previous MLLM jailbreak methods only uses a single image, which restricts the attack space: they cannot distribute harmful requests across multiple images, carry abundant information, or exploit additional visual reasoning tasks to distract MLLMs. To address these limitations, in this paper, we propose a compositional jailbreak framework, \textbf{DMN}, which leverages \textbf{D}istributed instruction, \textbf{M}ultimodal evidence and a \textbf{N}umber chain task to fully enhance the jailbreak performance. Extensive experiments show that DMN is highly effective for MLLM jailbreaking, e.g. achieving attack success rates of over 90% on GPT-4o, Gemini-2.5-pro and Claude Sonnet 4, surpassing other baselines by a large margin. This compositional, multi-image jailbreak strategy reveals fundamental weaknesses in their safety mechanisms.