Related papers: Negation-Induced Forgetting in LLMs

The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and subsequently, arithmetic reasoning). However, non-linguistic…

The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by…

Why do large language models sometimes output factual inaccuracies and exhibit erroneous reasoning? The brittleness of these models, particularly when executing long chains of reasoning, currently seems to be an inevitable price to pay for…

Contradictory results about the encoding of the semantic impact of negation in pretrained language models (PLMs). have been drawn recently (e.g. Kassner and Sch{\"u}tze (2020); Gubelmann and Handschuh (2022)). In this paper we focus rather…

Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive…

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

Many recent studies endeavor to improve open-source language models through imitation learning, and re-training on the synthetic instruction data from state-of-the-art proprietary models like ChatGPT and GPT-4. However, the innate nature of…

Large language models (LLMs) have achieved a degree of success in generating coherent and contextually relevant text, yet they remain prone to a significant challenge known as hallucination: producing information that is not substantiated…

Vision Language Models (VLMs) show impressive capabilities in integrating and reasoning with both visual and language data. But these models make mistakes. A common finding -- similar to LLMs -- is their tendency to hallucinate, i.e.,…

Recent claims suggest that large language models (LMs) underperform humans in comprehending minimally complex English statements (Dentella et al., 2024). Here, we revisit those findings and argue that human performance was overestimated,…

The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to the development of machine unlearning techniques that enable…

In Chomsky's provocative critique "The False Promise of CHATGPT," Large Language Models (LLMs) are characterized as mere pattern predictors that do not acquire languages via intrinsic causal and self-correction structures like humans,…

Multimodal learning can benefit from the representation power of pretrained Large Language Models (LLMs). However, state-of-the-art transformer based LLMs often ignore negations in natural language and there is no existing benchmark to…

Large Language Models (LLMs) distinguish themselves by quickly delivering information and providing personalized responses through natural language prompts. However, they also infer user demographics, which can raise ethical concerns about…

In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false…

The emergence of unveiling human-like behaviors in Large Language Models (LLMs) has led to a closer connection between NLP and human psychology. Scholars have been studying the inherent personalities exhibited by LLMs and attempting to…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

The proliferation of large language models (LLMs) can influence how historical narratives are disseminated and perceived. This study explores the implications of LLMs' responses on the representation of mass atrocity memory, examining…

Random Number Generation Tasks (RNGTs) are used in psychology for examining how humans generate sequences devoid of predictable patterns. By adapting an existing human RNGT for an LLM-compatible environment, this preliminary study tests…

Large language models (LLMs) are the result of a massive experiment in bottom-up, data-driven reverse engineering of language at scale. Despite their utility in a number of downstream NLP tasks, ample research has shown that LLMs are…