Related papers: Control the Temperature: Selective Sampling for Di…
Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…
Diverse outputs in text generation are necessary for effective exploration in complex reasoning tasks, such as code generation and mathematical problem solving. Such Pass@$k$ problems benefit from distinct candidates covering the solution…
Since the release of ChatGPT, large language models (LLMs) have demonstrated remarkable capabilities across various domains. A key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. This…
Beyond individual languages, multilingual natural language processing (NLP) research increasingly aims to develop models that perform well across languages generally. However, evaluating these systems on all the world's languages is…
Increasingly large datasets of robot actions and sensory observations are being collected to train ever-larger neural networks. These datasets are collected based on tasks and while these tasks may be distinct in their descriptions, many…
Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive…
Temperature is a major source of inaccuracy in high-sensitivity accelerometers and gravimeters. Active thermal control systems require power and may not be ideal in some contexts such as airborne or spaceborne applications. We propose a…
Selecting high-quality and diverse training samples from extensive datasets plays a crucial role in reducing training overhead and enhancing the performance of Large Language Models (LLMs). However, existing studies fall short in assessing…
Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingual prompting: a…
Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…
Obtaining multiple meaningfully diverse, high quality samples from Large Language Models for a fixed prompt remains an open challenge. Current methods for increasing diversity often only operate at the token-level, paraphrasing the same…
We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional…
Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather than a purely inference-time choice. Sampling temperature…
Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been…
Sampling is a common strategy for generating text from probabilistic models, yet standard ancestral sampling often results in text that is incoherent or ungrammatical. To alleviate this issue, various modifications to a model's sampling…
LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by generating multiple candidate programs and measuring their disagreement. However, existing…
The sampling temperature, a critical hyperparameter in large language models (LLMs), modifies the logits before the softmax layer, thereby reshaping the distribution of output tokens. Recent studies have challenged the Stochastic Parrots…
We conduct a preliminary study of the effect of GPT's temperature parameter on the diversity of GPT4-generated questions. We find that using higher temperature values leads to significantly higher diversity, with different temperatures…
This paper systematically compares different methods of deriving item-level predictions of language models for multiple-choice tasks. It compares scoring methods for answer options based on free generation of responses, various…
Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the additional computational and financial costs associated with…