Related papers: Mimicking How Humans Interpret Out-of-Context Sent…

Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on…

With adversarial or otherwise normal prompts, existing large language models (LLM) can be pushed to generate toxic discourses. One way to reduce the risk of LLMs generating undesired discourses is to alter the training of the LLM. This can…

The fundamental problem in toxicity detection task lies in the fact that the toxicity is ill-defined. This causes us to rely on subjective and vague data in models' training, which results in non-robust and non-accurate results: garbage in…

Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still treat toxicity as an intrinsic property of isolated text. This position paper…

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

Controllable and transparent text generation has been a long-standing goal in NLP. Almost as long-standing is a general idea for addressing this challenge: Parsing text to a symbolic representation, and generating from it. However, earlier…

A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for transparency and…

Recent progress in pre-trained language models led to systems that are able to generate text of an increasingly high quality. While several works have investigated the fluency and grammatical correctness of such models, it is still unclear…

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

Many real-world applications (e.g., note taking, search) require extracting a sentence or paragraph from a document and showing that snippet to a human outside of the source document. Yet, users may find snippets difficult to understand as…

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…

Lexical ambiguity presents a profound and enduring challenge to the language sciences. Researchers for decades have grappled with the problem of how language users learn, represent and process words with more than one meaning. Our work…

Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address…

Although there have been automated approaches and tools supporting toxicity censorship for social posts, most of them focus on detection. Toxicity censorship is a complex process, wherein detection is just an initial task and a user can…

Neural language models are increasingly deployed into APIs and websites that allow a user to pass in a prompt and receive generated text. Many of these systems do not reveal generation parameters. In this paper, we present methods to…

When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation…

We investigate the impact of using author context on textual sarcasm detection. We define author context as the embedded representation of their historical posts on Twitter and suggest neural models that extract these representations. We…

Platforms that support online commentary, from social networks to news sites, are increasingly leveraging machine learning to assist their moderation efforts. But this process does not typically provide feedback to the author that would…

Text detoxification is the task of transferring the style of text from toxic to neutral. While here are approaches yielding promising results in monolingual setup, e.g., (Dale et al., 2021; Hallinan et al., 2022), cross-lingual transfer for…