相关论文: Discovering Forbidden Topics in Language Models

Biosecurity evaluations of language models typically ask whether models produce hazardous output. This paper asks a complementary question: when a model refuses, is that refusal structurally sound, or does it disappear under modest changes…

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

We present a system for the Zero Resource Speech Challenge 2021, which combines a Contrastive Predictive Coding (CPC) with deep cluster. In deep cluster, we first prepare pseudo-labels obtained by clustering the outputs of a CPC network…

Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not. To perform open-set object recognition accurately, a key challenge is how to reduce the reliance on…

Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by…

Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dealing with short text datasets that lack co-occurring words.…

Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 problems based on the NPR Sunday Puzzle Challenge that requires…

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

We introduce Tempest, a multi-turn adversarial framework that models the gradual erosion of Large Language Model (LLM) safety through a tree search perspective. Unlike single-turn jailbreaks that rely on one meticulously engineered prompt,…

Information seeking demands iterative evidence gathering and reflective reasoning, yet large language models (LLMs) still struggle with it in open-web question answering. Existing prompting and supervised fine-tuning (SFT) methods remain…

The rise in malicious usage of large language models, such as fake content creation and academic plagiarism, has motivated the development of approaches that identify AI-generated text, including those based on watermarking or outlier…

Large Language Models (LLMs) are susceptible to jailbreak attacks where malicious prompts are disguised using ciphers and character-level encodings to bypass safety guardrails. While these guardrails often fail to interpret the encoded…

In this paper we present a model for unsupervised topic discovery in texts corpora. The proposed model uses documents, words, and topics lookup table embedding as neural network model parameters to build probabilities of words given topics,…

Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent…

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls…

Detecting life-threatening language is essential for safeguarding individuals in distress, promoting mental health and well-being, and preventing potential harm and loss of life. This paper presents an effective approach to identifying…

Detectives frequently engage in information detection and reasoning simultaneously when making decisions across various cases, especially when confronted with a vast amount of information. With the rapid development of large language…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for…