Related papers: Negation-Induced Forgetting in LLMs
Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensitive nature of their…
Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…
Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…
Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of…
Negations are key to determining sentence meaning, making them essential for logical reasoning. Despite their importance, negations pose a substantial challenge for large language models (LLMs) and remain underexplored. We constructed and…
When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…
Fine-tuning large language models (LLMs) can cause them to lose their general capabilities. However, the intrinsic mechanisms behind such forgetting remain unexplored. In this paper, we begin by examining this phenomenon by focusing on…
Generative Large Language Models (LLMs) have shown promising results in text annotation using zero-shot and few-shot learning. Yet these approaches do not allow the model to retain information from previous annotations, making each response…
A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying…
Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous research has focused on detecting and addressing negative…
The rise of Large Language Models (LLMs) like ChatGPT has advanced natural language processing, yet concerns about cognitive biases are growing. In this paper, we investigate the anchoring effect, a cognitive bias where the mind relies…
Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data, reinforcing biases, and producing harmful content. These risks have spurred interest in LLM…
Large Language Models (LLMs),such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation tasks. Recently, some research has suggested that LLMs may even be able to simulate human…
Large language models (LLMs) often require vast amounts of text to effectively acquire new knowledge. While continuing pre-training on large corpora or employing retrieval-augmented generation (RAG) has proven successful, updating an LLM…
Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To improve language models in this regard, we propose to…
Large language models (LLMs) are widely deployed as general-purpose tools, yet extended interaction can reveal behavioral patterns not captured by standard quantitative benchmarks. We present a qualitative case-study methodology for…
Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…
Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…
The performance of Large Language Models (LLMs) often degrades when crucial information is in the middle of a long context, a "lost-in-the-middle" phenomenon that mirrors the primacy and recency effects in human memory. We propose that this…
Large Language Models (LLMs) can memorize sensitive information, raising concerns about potential misuse. LLM Unlearning, a post-hoc approach to remove this information from trained LLMs, offers a promising solution to mitigate these risks.…