相关论文: Measuring and Controlling Instruction (In)Stabilit…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts. In this paper, we propose ExpertPrompting to elicit the potential of LLMs to answer as distinguished…

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans learn faster when…

This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners. Our system can adapt to users' language…

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

Training stability is of great importance to Transformers. In this work, we investigate the training dynamics of Transformers by examining the evolution of the attention layers. In particular, we track the attention entropy for each…

Safety architectures for language models increasingly rely on external monitors to detect errors and inject corrective signals at inference time. For such systems to function in interactive settings, models must be able to incorporate…

In recent years, prompting has quickly become one of the standard ways of steering the outputs of generative machine learning models, due to its intuitive use of natural language. In this work, we propose a system conditioned on embeddings…

Large-Language Models like GPT-3 have the potential to enable HCI designers and researchers to create more human-like and helpful chatbots for specific applications. But evaluating the feasibility of these chatbots and designing prompts…

In this study, we address the challenge of enabling large language models (LLMs) to consistently adhere to emotional support strategies in extended conversations. We focus on the steerability of the Llama-2 and Llama-3 suite of models,…

This paper introduces ChatbotManip, a novel dataset for studying manipulation in Chatbots. It contains simulated generated conversations between a chatbot and a (simulated) user, where the chatbot is explicitly asked to showcase…

Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it has a clear drawback: many soft tokens must be inserted into the input sequences to guarantee downstream performance. As a result, soft prompt tuning…

Mirroring is the behavior in which one person subconsciously imitates the gesture, speech pattern, or attitude of another. In conversations, mirroring often signals the speakers enjoyment and engagement in their communication. In chatbots,…

Corruption studies, the standard tool for evaluating chain-of-thought (CoT) faithfulness, infer which steps are ``computationally important'' from accuracy loss when steps are corrupted. We show that when benchmark chains end with an…

Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not…

Large Language Models (LLMs) have demonstrated promise in medical knowledge assessments, yet their practical utility in real-world clinical decision-making remains underexplored. In this study, we evaluated the performance of three…

A chatbot is an intelligent software application that automates conversations and engages users in natural language through messaging platforms. Leveraging artificial intelligence (AI), chatbots serve various functions, including customer…

Soft prompt tuning is a parameter-efficient method for adapting LLMs to specific tasks, but suffers from a lack of interpretability. Building on recent work on interpreting soft prompts (Ramati et al., 2024), we explore how training a…

Dialogue state tracking (DST) module is an important component for task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, especially with the wide…

Large language models (LLMs) are widely used for open-ended tasks, but underspecified prompts can lead to low-quality answers and additional interaction. This paper studies whether structured prompt design improves response quality while…