Related papers: Closing the Confidence-Faithfulness Gap in Large L…
Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…
Calibration, the alignment between model confidence and prediction accuracy, is critical for the reliable deployment of large language models (LLMs). Existing works neglect to measure the generalization of their methods to other prompt…
The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…
Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…
Large Language Models (LLMs), including ChatGPT and LLaMA, are susceptible to generating hallucinated answers in a confident tone. While efforts to elicit and calibrate confidence scores have proven useful, recent findings show that…
Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF). Unlike humans, whose…
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 reasoning models (LRMs) sometimes note in their chain of thought (CoT) that they may be under evaluation. Researchers worry that this verbalised evaluation awareness (VEA) causes models to adapt their outputs strategically, optimising…
Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs.…
Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large Language Models (LLMs). However, this critical property remains largely under-explored in…
Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…
Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…
The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…
Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the impact of this framing bias on LLM-based evaluation, where…
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…
As large language models (LLMs) are increasingly used for factual question-answering, it becomes more important for LLMs to have the capability to communicate the likelihood that their answer is correct. For these verbalized expressions of…
Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…
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…
Language and Vision-Language Models (LLMs/VLMs) have revolutionized the field of AI by their ability to generate human-like text and understand images, but ensuring their reliability is crucial. This paper aims to evaluate the ability of…
We investigate the use of large language models (LLMs) as post-processing modules for automatic speech recognition (ASR), focusing on their ability to perform error correction for disordered speech. In particular, we propose…