Related papers: Prefix Probing: Lightweight Harmful Content Detect…

Language models often struggle with idiomatic, figurative, or context-sensitive inputs, not because they produce flawed outputs, but because they misinterpret the input from the outset. We propose an input-only method for anticipating such…

Given a deep neural network image classification model that we treat as a black box, and an unlabeled evaluation dataset, we develop an efficient strategy by which the classifier can be evaluated. Randomly sampling and labeling instances…

We describe an extension of Earley's parser for stochastic context-free grammars that computes the following quantities given a stochastic context-free grammar and an input string: a) probabilities of successive prefixes being generated by…

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies in model performance.…

Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between…

Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these…

Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple -- a classifier is trained to predict some linguistic…

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to…

Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward…

Large language models (LLMs) have the potential to generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Consequently, detecting whether a text is…

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.…

Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While prefix-augmented inference is effective, it incurs two structural limitations: i) the prefix's…

Large Language Models are widely used for content moderation but often present certain over-sensitivity, leading to misclassification of benign content and rejecting safe user commands. While previous research attributes this issue…

The tremendous commercial potential of large language models (LLMs) has heightened concerns about their unauthorized use. Third parties can customize LLMs through fine-tuning and offer only black-box API access, effectively concealing…

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present…

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post…

Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a…

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…