The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
By Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
The paper investigates whether large language models’ refusal behavior in text transfers to tool‑calling contexts. A benchmark of 2,304 prompts across four domains compares text‑only, standard tool‑enabled, and adversarially framed tool‑enabled settings, revealing that 10–52 % of harmful requests refused in chat still lead to unsafe tool calls. The authors identify a refusal‑associated direction in the models’ residual stream, showing that lower activation along this direction predicts unsafe calls, but restoring the signal only partially mitigates the issue and often suppresses benign tool use.
By Ekagra Gupta, Raj Saha, Aniekan-Abasi Inyang, Adam Al Gharib
The paper introduces CarryOnBench, an interactive benchmark that tests whether large language models can revise their interpretation of user intent and recover utility while staying safe in multi‑turn conversations. Using 398 harmful‑looking queries with benign intents, the benchmark simulates 5,970 conversations across 14 models, evaluating both intent‑aligned utility and safety with a new metric called Ben‑Util. Results show that models often withhold information due to misinterpretation, but most can recover with clarifications, revealing failure modes such as unsafe and redundant recovery that single‑turn tests miss.
By Mingqian Zheng, Malia Morgan, Liwei Jiang, Carolyn Rose, Maarten Sap
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.
By Zhuoang Cai
arXiv:2604. 07223v2 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.
By Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen
arXiv:2609.36849v1 Announce Type: cross
Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...
By Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang
arXiv:2510. 14207v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm.
By Trilok Padhi, Pinxian Lu, Abdulkadir Erol, Tanmay Sutar, Gauri Sharma, Mina Sonmez, Munmun De Choudhury, Ugur Kursuncu
arXiv:2605.30913v2 Announce Type: replace-cross
Abstract: Large language models (LLMs) are increasingly deployed in conversational settings where user phrasing ranges from polite to casual to toxic,...
By Soorya Ram Shimgekar, Agam Goyal, Amruta Parulekar, Joshua Chen, Yian Wang, Navin Kumar, Hari Sundaram, Eshwar Chandrasekharan, Koustuv Saha
arXiv:2609.38389v1 Announce Type: cross
Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear...
By Yelyzaveta (Lisa), Husieva, Lauren Alvarez
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).
By Adarsh Kumarappan, Ananya Mujoo
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
By Md. Hasib Ur Rahman
The paper examines how automated safety systems unevenly flag harmful content, disproportionately labeling African American English as offensive and misclassifying content from drag queens and white nationalists. It identifies seven failure modes rooted in vocabulary-based harm detection and proposes an evaluation protocol that highlights gaps in performance across languages. Applied to five open systems in eleven languages, the study finds that none achieve native-speaker accuracy, and higher capability often increases discrimination, widening the disparity between best- and worst-served language communities.
By Gabriel Lars Sabadin, Dr Nicola Harding, Sarah Kingston