相关论文: Prompts have evil twins

Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt for a specific demand lacks theoretical support and relies…

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Both humans and large language models are able to learn language without explicit structural supervision. What inductive biases make this learning possible? We address this fundamental cognitive question by leveraging transformer language…

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the…

Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…

Hallucination, one kind of pathological translations that bothers Neural Machine Translation, has recently drawn much attention. In simple terms, hallucinated translations are fluent sentences but barely related to source inputs. Arguably,…

Large language models (LLMs) exhibit excellent ability to understand human languages, but do they also understand their own language that appears gibberish to us? In this work we delve into this question, aiming to uncover the mechanisms…

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Abductive reasoning is inference to the most plausible explanation. For example, if Jenny finds her house in a mess when she returns from work, and remembers that she left a window open, she can hypothesize that a thief broke into her house…

Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language. However, the learning environments and biases of current artificial learners and humans diverge in…

With the advent of Large Language Models (LLMs), generating rule-based data for real-world applications has become more accessible. Due to the inherent ambiguity of natural language and the complexity of rule sets, especially in long…

Temporary syntactic ambiguities arise when the beginning of a sentence is compatible with multiple syntactic analyses. We inspect to which extent neural language models (LMs) exhibit uncertainty over such analyses when processing…

Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions and/or relying on contextual cues and common-sense…

Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives…

Large Language Models (LLMs) have demonstrated an alarming ability to impersonate humans in conversation, raising concerns about their potential misuse in scams and deception. Humans have a right to know if they are conversing to an LLM. We…

Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer…

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH…

Background and Context. The increasing integration of large language models (LLMs) in computing education presents an emerging challenge in understanding how students use LLMs and craft prompts to solve computational tasks. Prior research…

A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLMs into providing intricate instructions to a malicious user…