相关论文: EVINCE: Optimizing Multi-LLM Dialogues Using Condi…

Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited…

In this paper, three laws are obtained for multiple-input multiple-output feedback systems, which are in entropy domain, frequency domain, and time domain, respectively. The system setup is that with causal plants and causal controllers.…

The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the…

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level…

This paper is a review of a particular approach to the method of maximum entropy as a general framework for inference. The discussion emphasizes the pragmatic elements in the derivation. An epistemic notion of information is defined in…

Large Language Models (LLMs) have shown significant advances in text generation but often lack the reliability needed for autonomous deployment in high-stakes domains like healthcare, law, and finance. Existing approaches rely on external…

Two hitherto disconnected threads of research, diverse exploration (DE) and maximum entropy RL have addressed a wide range of problems facing reinforcement learning algorithms via ostensibly distinct mechanisms. In this work, we identify a…

Long Context Language Models have drawn great attention in the past few years. There has been work discussing the impact of long context on Language Model performance: some find that long irrelevant context could harm performance, while…

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

The representations of conditional entropy and conditional mutual information are significant in explaining the unique effects among variables. While previous studies based on conditional contrastive sampling have effectively removed…

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to \textit{abstain} when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current…

Mental health issues are worsening in today's competitive society, such as depression and anxiety. Traditional healings like counseling and chatbots fail to engage effectively, they often provide generic responses lacking emotional depth.…

Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing large language model (LLM) reasoning, most methods lean toward exploitation, and increasingly encounter…

Recent advancements in generative Large Language Models(LLMs) have been remarkable, however, the quality of the text generated by these models often reveals persistent issues. Evaluating the quality of text generated by these models,…

Emotional Support Conversation (ESC) is a typical dialogue that can effectively assist the user in mitigating emotional pressures. However, owing to the inherent subjectivity involved in analyzing emotions, current non-artificial…

Uncertainty estimation in multi-LLM systems remains largely single-model-centric: existing methods quantify uncertainty within each model but do not adequately capture semantic disagreement across models. To address this gap, we propose…

Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and…

An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current…

Multi-Context Systems are an expressive formalism to model (possibly) non-monotonic information exchange between heterogeneous knowledge bases. Such information exchange, however, often comes with unforseen side-effects leading to violation…