We introduce LAMPO, a novel paradigm that leverages Large Language Models (LLMs) for solving few-shot multi-class ordinal classification tasks. Unlike conventional methods, which concatenate all demonstration examples with the test instance and prompt LLMs to produce the pointwise prediction, our framework uses the LLM as a preference machine that makes a relative comparative decision between the test instance and each demonstration. A self-supervised method is then introduced to aggregate these binary comparisons into the final ordinal decision. LAMPO addresses several limitations inherent in previous methods, including context length constraints, ordering biases, and challenges associated with absolute point-wise estimation. Extensive experiments on seven public datasets demonstrate LAMPO's remarkably competitive performance across a diverse spectrum of applications (e.g., movie review analysis and hate speech detection). Notably, in certain applications, the improvement can be substantial, exceeding 20% in an absolute term. Moreover, we believe LAMPO represents an interesting addition to the non-parametric application layered on top of LLMs, as it supports black-box LLMs without necessitating the outputting of LLM's internal states (e.g., embeddings), as seen in previous approaches.

An artificial intelligence system has already successfully predicted the outcome of hundreds of cases at the European Court of Human Rights, according to rsearchers from the University College London and the universities of Sheffield and Pennsylvania who developed it. According to reports, the AI "judge" examined data sets for 584 cases, with all cases either relating to torture, degrading treatment and privacy. The algorithm analyzed the English language information for each case and then made a decision – a decision that proved to be 79 percent accurate. The vast majority of applications lodged with ECHR are deemed inadmissible, due to the fact the applications don't meet the court's required criteria. This means that each year the court receives thousands of applications it must read through to determine admissibility.

A group of researchers from the University College London (UCL), University of Sheffield, and University of Pennsylvania, created an Artificial Intelligence system to judge 584 human rights cases and had released its findings recently. The cases analyzed by the AI method were previously heard at the European Court of Human Rights (ECHR) and were equally divided into violation and non-violation cases to prevent bias. European Court of Human Rights in Strasbourg, France (Image Credit: ECHR) So how did the AI judge perform? Basing its judgment on the case text, the AI judge managed to predict the decisions on the cases with 79% accuracy. That means, it concurred with the decisions of human judges 8 out of 10 times.

An artificial intelligence algorithm has predicted the outcome of human rights trials with 79 percent accuracy, according to a study published today in PeerJ Computer Science. Developed by researchers from the University College London (UCL), the University of Sheffield, and the University of Pennsylvania, the system is the first of its kind trained solely on case text from a major international court, the European Court of Human Rights (ECtHR). "Our motivation was twofold," co-author Vasileios Lampos of UCL Computer Science told Digital Trends. "It first starts with scientific curiosity." In other words, would it even be possible to create such an AI judge?

The judicial decisions of the European Court of Human Rights (ECtHR) have been predicted to 79% accuracy using an artificial intelligence (AI) method developed by researchers at UCL, the University of Sheffield and the University of Pennsylvania. The method is the first to predict the outcomes of a major international court by automatically analysing case text using a machine learning algorithm. The study behind it was published today in PeerJ Computer Science. "We don't see AI replacing judges or lawyers, but we think they'd find it useful for rapidly identifying patterns in cases that lead to certain outcomes. It could also be a valuable tool for highlighting which cases are most likely to be violations of the European Convention on Human Rights," explained Dr Nikolaos Aletras, who led the study at UCL Computer Science.