Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2602.06623

Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention

Himanshu Singh·Ziwei Xu·A. V. Subramanyam·Mohan Kankanhalli
View original source ↗Read source document ↗Export metadata ↓

Abstract

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often subtle and context-dependent, making it difficult to detect at the token level or through coarse sentence-level signals. Moreover, efforts to mitigate toxicity often face a trade-off between safety and the coherence, or fluency of the generated text. In this work, we present a targeted subspace intervention strategy for identifying and suppressing hidden toxic patterns from underlying model representations, while preserving overall ability to generate safe fluent content. On the RealToxicityPrompts, our method achieves strong mitigation performance compared to existing baselines, with minimal impact on inference complexity. Across multiple LLMs, our approach reduces toxicity of state-of-the-art detoxification systems by 8-20%, while maintaining comparable fluency. Through extensive quantitative and qualitative analyses, we show that our approach achieves effective toxicity reduction without impairing generative performance, consistently outperforming existing baselines.

Explore related subjects

cs.CLcs.CR

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Himanshu Singh, Ziwei Xu, A. V. Subramanyam, Mohan Kankanhalli. 2026-02-06. Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention. https://arxiv.org/abs/2602.06623

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration

Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing more affordable pretraining methods. One notable advancement in this area is the Cramming technique (Geiping and Goldstein, 2022), which enables the pretraining of BERT-style language models using just one GPU in a single day. Building on this innovative approach, we introduce the Dependency Agreement Cramming (DA-Cramming), an efficient framework that integrates information about dependency agreements into the pretraining process. Unlike existing methods that leverage similar semantic information during finetuning, our approach represents a pioneering effort focusing on enhancing the foundational language understanding with semantic information during pretraining. We meticulously design a dual-stage pretraining work flow with four dedicated submodels to capture representative dependency agreements at the chunk level, effectively transforming these agreements into embeddings to benefit the pretraining. Extensive empirical results demonstrate that our method significantly outperforms previous methods across various tasks.

cs.CL↗
arXiv2026

BigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?

We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities. This benchmark addresses the gap in current evaluations that often overlook the ability of models to comprehend and produce code constrained by computational complexity. BigO(Bench) includes tooling to infer the algorithmic complexity of any Python function from profiling measurements, including human- or LLM-generated solutions. BigO(Bench) also includes of set of 3,105 coding problems and 1,190,250 solutions from Code Contests annotated with inferred (synthetic) time and space complexity labels from the complexity framework, as well as corresponding runtime and memory footprint values for a large set of input sizes. We present results from evaluating multiple state-of-the-art language models on this benchmark, highlighting their strengths and weaknesses in handling complexity requirements. In particular, token-space reasoning models are unrivaled in code generation but not in complexity understanding, hinting that they may not generalize well to tasks for which no reward was given at training time.

cs.CL↗
arXiv2026

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning. However, existing attempts to unify these paradigms remain narrow in scope, typically limited to open-domain QA with fixed retrieval settings, which constrains generalization to broader domains. To address this limitation, we propose UR$^2$ (Unified RAG and Reasoning)), a general reinforcement learning framework that dynamically coordinates retrieval and reasoning. UR$^2$ introduces two key designs: a difficulty-aware curriculum that selectively invokes retrieval only for challenging instances, and a hybrid knowledge access strategy that combines domain-specific offline corpora with on-the-fly LLM-generated summaries. Together, these components mitigate the imbalance between retrieval and reasoning and improve robustness to noisy information. Experiments on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks show that UR$^2$, built on Qwen-2.5-3/7B and LLaMA-3.1-8B, consistently outperforms existing RAG and RL baselines, and achieves performance comparable to GPT-4o-mini and GPT-4.1-mini on several benchmarks. Code, models, and data are available at https://github.com/Tsinghua-dhy/UR2.

cs.CL↗