Related papers: Optimizing Temperature for Language Models with Mu…

Large Language Models (LLMs) like GPT-4o can help automate text classification tasks at low cost and scale. However, there are major concerns about the validity and reliability of LLM outputs. By contrast, human coding is generally more…

Large Language Models (LLMs), such as GPT models, are increasingly used in software engineering for various tasks, such as code generation, requirements management, and debugging. While automating these tasks has garnered significant…

Large language models (LLMs) are applied to all sorts of creative tasks, and their outputs vary from beautiful, to peculiar, to pastiche, into plain plagiarism. The temperature parameter of an LLM regulates the amount of randomness, leading…

Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding…

A wide body of evidence shows that human language processing difficulty is predicted by the information-theoretic measure surprisal, a word's negative log probability in context. However, it is still unclear how to best estimate these…

Temperature of a finite-sized system fluctuates due to the thermal fluctuations. However, a systematic mathematical framework for measuring or estimating the temperature is still underdeveloped. Here, we incorporate the estimation theory in…

Large language models (LLMs) are becoming a one-fits-many solution, but they sometimes hallucinate or produce unreliable output. In this paper, we investigate how hypothesis ensembling can improve the quality of the generated text for the…

Mixed Integer Programming (MIP) has been extensively applied in areas requiring mathematical solvers to address complex instances within tight time constraints. However, as the problem scale increases, the complexity of model formulation…

We consider the problem of aligning a large language model (LLM) to model the preferences of a human population. Modeling the beliefs, preferences, and behaviors of a specific population can be useful for a variety of different…

Autoregressive language models typically use temperature parameter at inference to shape the probability distribution and control the randomness of the text generated. After the text was generated, this parameter can be estimated using…

Generative models of complex systems often require post-hoc parameter adjustments to produce useful outputs. For example, energy-based models for protein design are sampled at an artificially low ''temperature'' to generate novel,…

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…

The key challenge in multispectral radiation thermometry is accurately measuring emissivity. Traditional constrained optimization methods often fail to meet practical requirements in terms of precision, efficiency, and noise resistance.…

Since the internal temperature is less accessible than surface temperature, there is an urgent need to develop accurate and real-time estimation algorithms for better thermal management and safety. This work presents a novel framework for…

Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer,…

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Inductive reasoning - the process of inferring general rules from a small number of observations - is a fundamental aspect of human intelligence. Recent works suggest that large language models (LLMs) can engage in inductive reasoning by…

Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified that tokens within LLMs…

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing…

We investigated whether large language models (LLMs) can develop data validation tests. We considered 96 conditions each for both GPT-3.5 and GPT-4, examining different prompt scenarios, learning modes, temperature settings, and roles. The…