Related papers: Asking Forever: Universal Activations Behind Turn …

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of…

A conversation with a large language model (LLM) is a sequence of prompts and responses, with each response generated from the preceding conversation. AI agents build such conversations automatically: given an initial human prompt, a…

Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or conversational strategies. Meanwhile, abliteration techniques (also known as targeted ablations of…

Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning…

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, despite their impressive capabilities, they still possess limitations,…

Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Several recent works argue that LLMs have a universal truth direction where true and false statements are linearly separable in the activation space of the model. It has been demonstrated that linear probes trained on a single hidden state…

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken…

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

Large Language Models (LLMs) have made it possible for recommendation systems to interact with users in open-ended conversational interfaces. In order to personalize LLM responses, it is crucial to elicit user preferences, especially when…

Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access…

Reinforcement Learning (RL) agents often struggle in sparse-reward environments where traditional exploration strategies fail to discover effective action sequences. Large Language Models (LLMs) possess procedural knowledge and reasoning…

Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the…

This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings. Using a PRISMA-inspired framework, we systematically reviewed nearly 250 scholarly sources, capturing the state of…

Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents…

Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversations. While recent work has explored the use of LLMs in…