Related papers: Asking Forever: Universal Activations Behind Turn …
Human-LLM conversations are increasingly becoming more pervasive in peoples' professional and personal lives, yet many users still struggle to elicit helpful responses from LLM Chatbots. One of the reasons for this issue is users' lack of…
Given the advancements in conversational artificial intelligence, the evaluation and assessment of Large Language Models (LLMs) play a crucial role in ensuring optimal performance across various conversational tasks. In this paper, we…
Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole,…
Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…
In the era of rapid generative AI development, interactions with large language models (LLMs) pose increasing risks of misuse. Prior research has primarily focused on attacks using template-based prompts and optimization-oriented methods,…
Model collapse, a phenomenon characterized by performance degradation due to iterative training on synthetic data, has been widely studied. However, its implications for bias amplification, the progressive intensification of pre-existing…
This paper explores the impact of extending input lengths on the capabilities of Large Language Models (LLMs). Despite LLMs advancements in recent times, their performance consistency across different input lengths is not well understood.…
Multi-turn prompt injection attacks distribute malicious intent across multiple conversation turns, exploiting the assumption that each turn is evaluated independently. While single-turn detection has been extensively studied, no published…
Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn agent scenarios, where LLMs erroneously mimic their own previous responses as few-shot…
In an era where single large language models have dominated the landscape of artificial intelligence for years, multi-agent systems arise as new protagonists in conversational task-solving. While previous studies have showcased their…
With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…
We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow. Unlike jailbreaks or prompt injection, Overflow arises under ordinary interaction settings…
This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements…
Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effective clarification. However, existing interactive…
Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition (ICD), a…
In conversational search, agents can interact with users by asking clarifying questions to increase their chance to find better results. Many recent works and shared tasks in both NLP and IR communities have focused on identifying the need…
The transformer architecture has become the foundation of modern Large Language Models (LLMs), yet its theoretical properties are still not well understood. As with classic neural networks, a common approach to improve these models is to…
Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…
The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations. The traditional setting limits each participant to one message at a time and requires constant human participation. This fails to reflect a…
Large Language Models (LLMs) have achieved remarkable success in reasoning tasks with the development of prompting methods. However, existing prompting approaches cannot reuse insights of solving similar problems and suffer from accumulated…