相关论文: Human vs. machine -- 1:3. Joint analysis of classi…
The inference of astrophysical and cosmological properties from the Lyman-$\alpha$ forest conventionally relies on summary statistics of the transmission field that carry useful but limited information. We present a deep learning framework…
In inference problems, we often have domain knowledge which allows us to define summary statistics that capture most of the information content in a dataset. In this paper, we present a hybrid approach, where such physics-based summaries…
Summary assessment involves evaluating how well a generated summary reflects the key ideas and meaning of the source text, requiring a deep understanding of the content. Large Language Models (LLMs) have been used to automate this process,…
The Lyman-$\alpha$ forest refers to the series of absorption features observed in the spectra of distant quasars that are produced by neutral hydrogen in the intergalactic medium. Observed over a wide range of redshifts with both ground-…
The ability to compress observational data and accurately estimate physical parameters relies heavily on informative summary statistics. In this paper, we introduce the use of mutual information (MI) as a means of evaluating the quality of…
Evaluating text summarization has been a challenging task in natural language processing (NLP). Automatic metrics which heavily rely on reference summaries are not suitable in many situations, while human evaluation is time-consuming and…
Numerical hydrodynamical simulations have proven a successful means of reproducing many of the statistical properties of the Lyman-Alpha forest as measured in high redshift quasar spectra. Pseudo-hydrodynamical methods based only on…
Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization…
Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of…
Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of the summary is not…
Evaluating multi-document summarization (MDS) quality is difficult. This is especially true in the case of MDS for biomedical literature reviews, where models must synthesize contradicting evidence reported across different documents. Prior…
Machine learning (ML) is often viewed as a black-box regression technique that is unable to provide considerable scientific insight. ML models are universal function approximators and - if used correctly - can provide scientific information…
We test a method to reduce unwanted sample variance when predicting Lyman-$\alpha$ (ly$\alpha$) forest power spectra from cosmological hydrodynamical simulations. Sample variance arises due to sparse sampling of modes on large scales and…
The parameterization of moist convection contributes to uncertainty in climate modeling and numerical weather prediction. Machine learning (ML) can be used to learn new parameterizations directly from high-resolution model output, but it…
Recent studies have found that summaries generated by large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. Therefore, we study an LLM-as-reference…
Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard datasets. While these PLMs excel in automatic evaluations, they frequently underperform in human evaluations, indicating a deviation between…
Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess…
Lyman-$\alpha$(Ly$\alpha$) forest in the spectra of distant quasars encodes the information of the underlying cosmic density field at smallest scales. The modelling of the upcoming large and high-fidelity forest data using cosmological…
There is a vast literature on the determinants of subjective wellbeing. International organisations and statistical offices are now collecting such survey data at scale. However, standard regression models explain surprisingly little of the…
Observations of the Lyman-$\alpha$ (Ly$\alpha$) forest from spectroscopic surveys such as BOSS/eBOSS, or the ongoing DESI, offer a unique window to study the growth of structure on megaparsec scales. Interpretation of these measurements is…