Related papers: Evaluating Shutdown Avoidance of Language Models i…
Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…
Multi-turn interactions with large language models typically retain the assistant's own past responses in the conversation history. In this work, we revisit this design choice by asking whether large language models benefit from…
With the help of Chain-of-Thought (CoT) prompting, Large Language Models (LLMs) have achieved remarkable performance on various reasoning tasks. However, most of them have been evaluated under noise-free context and the dilemma for LLMs to…
Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…
Amidst the growing interest in developing task-autonomous AI for automated mental health care, this paper addresses the ethical and practical challenges associated with the issue and proposes a structured framework that delineates levels of…
Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive judgments? Existing evaluations emphasize problem-solving accuracy, overlooking the fragmented…
While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…
Dialogue data has been a key source for understanding learning processes, offering critical insights into how students engage in collaborative discussions and how these interactions shape their knowledge construction. The advent of Large…
Large Language Models, such as Generative Pre-trained Transformer 3 (aka. GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words.…
Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning…
With an evergrowing number of LLMs reporting superlative performance for English, their ability to perform equitably for different dialects of English ($\textit{i.e.}$, dialect robustness) needs to be ascertained. Specifically, we use…
Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state…
Language models are increasingly deployed in interactive settings where users reason about facts over time rather than in isolation. In such scenarios, correct behavior requires models to maintain and update implicit temporal assumptions…
Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…
Recent advancements in the field of large language models, particularly through the Chain of Thought (CoT) approach, have demonstrated significant improvements in solving complex problems. However, existing models either tend to sacrifice…
U.S. national security customers have begun to utilize large language models, including enterprise versions of ``off-the-shelf'' models (e.g., ChatGPT) familiar to the public. This uptake will likely accelerate. However, recent studies…
Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…
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…
Time is a crucial factor in modelling dynamic behaviours of intelligent agents: activities have a determined temporal duration in a real-world environment, and previous actions influence agents' behaviour. In this paper, we propose a…
Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient…