相关论文: Automatically Finding and Validating Unexpected Si…

Drawing from the resources of psychoanalysis and critical media studies, in this paper we develop an analysis of Large Language Models (LLMs) as automated subjects. We argue the intentional fictional projection of subjectivity onto LLMs can…

The volume and diversity of digital information have led to a growing reliance on Machine Learning techniques, such as Natural Language Processing, for interpreting and accessing appropriate data. While vector and graph embeddings represent…

Recently efforts have been made by social media platforms as well as researchers to detect hateful or toxic language using large language models. However, none of these works aim to use explanation, additional context and victim community…

The recent proliferation of research into transformer based natural language processing has led to a number of studies which attempt to detect the presence of human-like cognitive behavior in the models. We contend that, as is true of human…

The achievements of Large Language Models in Natural Language Processing, especially for high-resource languages, call for a better understanding of their characteristics from a cognitive perspective. Researchers have attempted to evaluate…

Generative language models have improved drastically, and can now produce realistic text outputs that are difficult to distinguish from human-written content. For malicious actors, these language models bring the promise of automating the…

Automatic side-by-side evaluation has emerged as a promising approach to evaluating the quality of responses from large language models (LLMs). However, analyzing the results from this evaluation approach raises scalability and…

We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large…

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.…

In many real-world applications, large language models (LLMs) operate as independent agents without interaction, thereby limiting coordination. In this setting, we examine how prompt framing influences decisions in a threshold voting task…

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…

We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries…

Prompt engineering is a challenging yet crucial task for optimizing the performance of large language models on customized tasks. It requires complex reasoning to examine the model's errors, hypothesize what is missing or misleading in the…

Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while there has been emphasis on data quantity, less attention has…

Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert…

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction…

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…

Systematic reviews of interventions are important tools for synthesizing evidence from multiple studies. They serve to increase power and improve precision, in the same way that larger studies can do, but also to establish the consistency…