Related papers: BAIT: Boundary-Guided Disclosure Escalation via Se…
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…
Jailbreak attacks bypass the guardrails of large language models to produce harmful outputs. In this paper, we ask whether the model outputs produced by existing jailbreaks are actually useful. For example, when jailbreaking a model to give…
Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…
With the development of natural language processing (NLP), large language models (LLMs) are becoming increasingly popular. LLMs are integrating more into everyday life, raising public concerns about their security vulnerabilities.…
Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or…
Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If…
Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…
Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack…
Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However, restricting the objective as inducing fixed targets…
With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…
Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique ``jailbreak prompt'' can circumvent safety-aligned measures and induce LLMs to output malicious content.…
Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…
We introduce Backtrackable Inprocessing (BI), a framework that enables applying inprocessing under the current trail at any decision level, at any point during incremental SAT solving. Our approach lifts the long-standing restriction that…
Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…
Pre-trained Transformers have enabled impressive breakthroughs in generating long and fluent text, yet their outputs are often "rambling" without coherently arranged content. In this work, we present a novel content-controlled text…
We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, we expect models to not only answer questions, but also produce…
The rise of Large Audio Language Models (LAMs) brings both potential and risks, as their audio outputs may contain harmful or unethical content. However, current research lacks a systematic, quantitative evaluation of LAM safety especially…
Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements hinder deployment on constrained resources. To enhance efficiency,…
Multi-step reasoning ability of large language models is crucial in tasks such as math and tool utilization. Current researches predominantly focus on enhancing model performance in these multi-step reasoning tasks through fine-tuning with…