Linear Programming (LP) problems aim to find the optimal solution to an objective under constraints. These problems typically require domain knowledge, mathematical skills, and programming ability, presenting significant challenges for non-experts. This study explores the efficiency of Large Language Models (LLMs) in generating solver-specific LP code. We propose CHORUS, a retrieval-augmented generation (RAG) framework for synthesizing Gurobi-based LP code from natural language problem statements. CHORUS incorporates a hierarchical tree-like chunking strategy for theoretical contents and generates additional metadata based on code examples from documentation to facilitate self-contained, semantically coherent retrieval. Two-stage retrieval approach of CHORUS followed by cross-encoder reranking further ensures contextual relevance. Finally, expertly crafted prompt and structured parser with reasoning steps improve code generation performance significantly. Experiments on the NL4Opt-Code benchmark show that CHORUS improves the performance of open-source LLMs such as Llama3.1 (8B), Llama3.3 (70B), Phi4 (14B), Deepseek-r1 (32B), and Qwen2.5-coder (32B) by a significant margin compared to baseline and conventional RAG. It also allows these open-source LLMs to outperform or match the performance of much stronger baselines-GPT3.5 and GPT4 while requiring far fewer computational resources. Ablation studies further demonstrate the importance of expert prompting, hierarchical chunking, and structured reasoning.

This paper explores a new black-box, zero-shot language model inversion problem and proposes an innovative framework for prompt reconstruction using only text outputs from a language model. Leveraging a large language model alongside an optimization algorithm, the proposed method effectively recovers prompts with minimal resources. Experimental results on several datasets derived from public sources indicate that the proposed approach achieves high-quality prompt recovery and generates prompts more similar to the originals than current state-of-the-art methods. Additionally, the use-case study demonstrates the method's strong potential for generating high-quality text data.

A song about immigrants whose music, vocals and artwork were entirely generated using artificial intelligence has made the Top 50 most listened to songs in Germany, in what may be a first for a leading music market. Verknallt in einen Talahon is a parody song that weaves modern lyrics – many of them based around racial stereotypes about immigrants – with 60s schlager pop. The song is No 48 in Germany, the world's fourth largest music market. Less than a month after its release, the song has 3.5m streams on Spotify and is No 3 on the streaming platform's global viral chart. Its creator, Josua Waghubinger, who goes by the artist name Butterbro, said he made the song's chorus by feeding his own lyrics into Udio, a generative artificial intelligence tool that can generate vocals and instrumentation from simple text prompts.

We apply foundation models to data discovery and exploration tasks. Foundation models are large language models (LLMs) that show promising performance on a range of diverse tasks unrelated to their training. We show that these models are highly applicable to the data discovery and data exploration domain. When carefully used, they have superior capability on three representative tasks: table-class detection, column-type annotation and join-column prediction. On all three tasks, we show that a foundation-model-based approach outperforms the task-specific models and so the state of the art. Further, our approach often surpasses human-expert task performance. We investigate the fundamental characteristics of this approach including generalizability to several foundation models, impact of non-determinism on the outputs and syntactic/semantic signals. All in all, this suggests a future direction in which disparate data management tasks can be unified under foundation models.

This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects. We first formalize stylistic triggers - currently missing in the literature. Second, we explore how to develop stylistic triggers in the audio domain by proposing JingleBack. Our experiments confirm the effectiveness of the attack, achieving a 96% attack success rate. Our code is available in https://github.com/skoffas/going-in-style.

In fact, a recent study named it the highest earning song on Spotify in the UK, despite it being released by The Killers 20 years ago. The track has so far brought the Las Vegas-born band more than £1 million in royalties ($1,254,087) through the streaming service. Indeed, since 2004, 'Mr Brightside' has spent 358 non-consecutive weeks in the UK singles charts, and is currently at number 62. But why exactly has Mr Brightside stood the test of time? MailOnline takes a look at the science behind this rock anthem.

We decided to have some fun with ChatGPT, the scary-good chatbot from OpenAI that's been garnering headlines. We fed it a fake letter, cobbled together with common tropes, and asked it to reply in a few different ways. I'm recently engaged and in the throes of planning my early 2024 wedding. My handsome fiancé, the timing, my mother's own hand-me-down ring--it's all felt like a perfect fairytale. Until I heard what my mother-in-law has in store for us.

The artificial intelligence bot which Nick Cave accused of making a'grotesque mockery' of his work has hit back at the musician by insisting it'tries its best to generate text that is coherent, creative and conveys a message'. Cave left a scathing review of ChatGPT's rendition of his work, describing the lyrics after fans asked it to replicate his style of music. He's one of many musicians fans are asking the bot to mimic, to see if it can capture the magic of songs legitimately produced by the artist. ChatGPT collates huge swathes of data which allows it to predict phrases and words that are likely to be used in an artist's repertoire. When provided a prompt, such as asking it to create song lyrics for a certain artist, it sweeps the database for all known previous works by the artist and collates sentences using phrases, terms and themes frequently used in association with the musician.

As the sun rises over the island of American Samoa, a chorus of animal voices drifts upward. They're not the calls of birds, though -- the purrs, clicks and groans are coming from under the water. New research shows how automation can make it increasingly easy to eavesdrop on the fish making the sounds and uncover how their environment impacts them. Jill Munger first heard about fish that make sounds while she was an undergraduate student. A veteran researcher told her about marine acoustics.

This is an Inside Science story. As the sun rises over the island of American Samoa, a chorus of animal voices drifts upward. They're not the calls of birds, though -- the purrs, clicks and groans are coming from under the water. New research shows how automation can make it increasingly easy to eavesdrop on the fish making the sounds and uncover how their environment impacts them. Jill Munger first heard about fish that make sounds while she was an undergraduate student.