相关论文: Detecting the Disturbance: A Nuanced View of Intro…

Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be…

There has been recent interest in whether large language models (LLMs) can introspect about their own internal states. Such abilities would make LLMs more interpretable, and also validate the use of standard introspective methods in…

We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address…

A hallmark of human intelligence is Introspection-the ability to assess and reason about one's own cognitive processes. Introspection has emerged as a promising but contested capability in large language models (LLMs). However, current…

Large language models (LLMs) exhibit compelling linguistic behaviour, and sometimes offer self-reports, that is to say statements about their own nature, inner workings, or behaviour. In humans, such reports are often attributed to a…

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers.…

Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-box methods compress high-dimensional…

Large language models (LLMs) exhibit advanced reasoning skills, enabling robots to comprehend natural language instructions and strategically plan high-level actions through proper grounding. However, LLM hallucination may result in robots…

We uncover a latent capacity for introspection in a Qwen 32B model, demonstrating that the model can detect when concepts have been injected into its earlier context and identify which concept was injected. While the model denies injection…

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs). Performance is on par with the largest and most advanced LLMs currently available, but…

Large language model (LLM) systems suffer from the models' unstable ability to generate valid and factual content, resulting in hallucination generation. Current hallucination detection methods heavily rely on out-of-model information…

Large Language Models (LLMs) have demonstrated impressive mathematical reasoning capabilities, yet their performance remains brittle to minor variations in problem description and prompting strategy. Furthermore, reasoning is vulnerable to…

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…

Large Language Models (LLMs) have revolutionised natural language processing, exhibiting impressive human-like capabilities. In particular, LLMs are capable of "lying", knowingly outputting false statements. Hence, it is of interest and…

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to…

LLMs have made significant progress in the field of mathematical reasoning, but whether they have true the mathematical understanding ability is still controversial. To explore this issue, we propose a new perturbation framework to evaluate…

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…