Rule-based rewards offer a promising strategy for improving reinforcement learning from human feedback (RLHF), but current approaches often rely on manual rule engineering. We present AutoRule, a fully automated method for extracting rules from preference feedback and formulating them into rule-based rewards. AutoRule extraction operates in three stages: it leverages a reasoning model to interpret user preferences, identifies candidate rules from the reasoning chain of these interpretations, and synthesizes them into a unified rule set. Leveraging the finalized rule set, we employ language-model verifiers to compute the fraction of rules satisfied by each output, using this metric as an auxiliary reward alongside the learned reward model during policy optimization. Training a Llama-3-8B model with AutoRule results in a 28.6\% relative improvement in length-controlled win rate on AlpacaEval2.0, and a 6.1\% relative gain in second-turn performance on a held-out MT-Bench subset, compared to a GRPO baseline trained with the same learned reward model but without the rule-based auxiliary reward. Our analysis confirms that the extracted rules exhibit good agreement with dataset preference. We find that AutoRule demonstrates reduced reward hacking compared to a learned reward model when run over two episodes. Finally, our case study suggests that the extracted rules capture unique qualities valued in different datasets. The extracted rules are provided in the appendix, and the code is open-sourced at https://github.com/cxcscmu/AutoRule.

Breakthroughs in text-to-music generation models are transforming the creative landscape, equipping musicians with innovative tools for composition and experimentation like never before. However, controlling the generation process to achieve a specific desired outcome remains a significant challenge. Even a minor change in the text prompt, combined with the same random seed, can drastically alter the generated piece. In this paper, we explore the application of existing text-to-music diffusion models for instrument editing. Specifically, for an existing audio track, we aim to leverage a pretrained text-to-music diffusion model to edit the instrument while preserving the underlying content. Based on the insight that the model first focuses on the overall structure or content of the audio, then adds instrument information, and finally refines the quality, we show that selecting a well-chosen intermediate timestep, identified through an instrument classifier, yields a balance between preserving the original piece's content and achieving the desired timbre. Our method does not require additional training of the text-to-music diffusion model, nor does it compromise the generation process's speed.

Despite progress in comment-aware multimodal and multilingual summarization for English and Chinese, research in Indian languages remains limited. This study addresses this gap by introducing COSMMIC, a pioneering comment-sensitive multimodal, multilingual dataset featuring nine major Indian languages. COSMMIC comprises 4,959 article-image pairs and 24,484 reader comments, with ground-truth summaries available in all included languages. Our approach enhances summaries by integrating reader insights and feedback. We explore summarization and headline generation across four configurations: (1) using article text alone, (2) incorporating user comments, (3) utilizing images, and (4) combining text, comments, and images. To assess the dataset's effectiveness, we employ state-of-the-art language models such as LLama3 and GPT-4. We conduct a comprehensive study to evaluate different component combinations, including identifying supportive comments, filtering out noise using a dedicated comment classifier using IndicBERT, and extracting valuable insights from images with a multilingual CLIP-based classifier. This helps determine the most effective configurations for natural language generation (NLG) tasks. Unlike many existing datasets that are either text-only or lack user comments in multimodal settings, COSMMIC uniquely integrates text, images, and user feedback. This holistic approach bridges gaps in Indian language resources, advancing NLP research and fostering inclusivity.

Evaluating open-ended long-form generation is challenging because it is hard to define what clearly separates good from bad outputs. Existing methods often miss key aspects like coherence, style, or relevance, or are biased by pretraining data, making open-ended long-form evaluation an underexplored problem. To address this gap, we propose PrefBERT, a scoring model for evaluating open-ended long-form generation in GRPO and guiding its training with distinct rewards for good and bad outputs. Trained on two response evaluation datasets with diverse long-form styles and Likert-rated quality, PrefBERT effectively supports GRPO by offering better semantic reward feedback than traditional metrics ROUGE-L and BERTScore do. Through comprehensive evaluations, including LLM-as-a-judge, human ratings, and qualitative analysis, we show that PrefBERT, trained on multi-sentence and paragraph-length responses, remains reliable across varied long passages and aligns well with the verifiable rewards GRPO needs. Human evaluations confirm that using PrefBERT as the reward signal to train policy models yields responses better aligned with human preferences than those trained with traditional metrics. Our code is available at https://github.com/zli12321/long_form_rl.

How can we detect when global events fundamentally reshape public discourse? This study introduces a topological framework for identifying structural change in media narratives using persistent homology. Drawing on international news articles surrounding major events - including the Russian invasion of Ukraine (Feb 2022), the murder of George Floyd (May 2020), the U.S. Capitol insurrection (Jan 2021), and the Hamas-led invasion of Israel (Oct 2023) - we construct daily co-occurrence graphs of noun phrases to trace evolving discourse. Each graph is embedded and transformed into a persistence diagram via a Vietoris-Rips filtration. We then compute Wasserstein distances and persistence entropies across homological dimensions to capture semantic disruption and narrative volatility over time. Our results show that major geopolitical and social events align with sharp spikes in both H0 (connected components) and H1 (loops), indicating sudden reorganization in narrative structure and coherence. Cross-correlation analyses reveal a typical lag pattern in which changes to component-level structure (H0) precede higher-order motif shifts (H1), suggesting a bottom-up cascade of semantic change. An exception occurs during the Russian invasion of Ukraine, where H1 entropy leads H0, possibly reflecting top-down narrative framing before local discourse adjusts. Persistence entropy further distinguishes tightly focused from diffuse narrative regimes. These findings demonstrate that persistent homology offers a mathematically principled, unsupervised method for detecting inflection points and directional shifts in public attention - without requiring prior knowledge of specific events. This topological approach advances computational social science by enabling real-time detection of semantic restructuring during crises, protests, and information shocks.

The AI analyses the track and intelligently filters out vocals, making it ideal for even novices to create karaoke tracks, remixes, or instrumental versions of songs. The Audio Enhancer by HitPaw Univd boosts audio quality by eliminating unwanted background noise and enhancing clarity. Whether you're working with podcasts, voiceovers, or music tracks, this feature ensures your audio sounds professional by automatically adjusting volume levels, reducing distortion, and fine-tuning the sound.

Victoria Aveyard's eyes avoid the camera when she slams her large white binder on the table, weighed down with a 1,000-page draft of her latest work in progress. The stack is heavy, made clear by her audible sigh as she splits the thick manuscript in half. Aveyard, the New York Times bestselling young adult fantasy author of the Red Queen series, doesn't say a single word in the video, but her captions on the screen speak volumes. "Using GenAI to write a book doesn't make you a writer, it makes you a thief," reads one. "Don't use generative-AI to make tropey, regurgitated romantasy sludge that you can then launder through the self-publishing industry in order to backdoor your way into a traditional publishing deal," Aveyard tells her over 460,000 followers on TikTok in another video posted on May 27. "Authors talk."

Up to seven out of 10 streams of artificial intelligence-generated music on the Deezer platform are fraudulent, according to the French streaming platform. The company said AI-made music accounts for just 0.5% of streams on the music streaming platform but its analysis shows that fraudsters are behind up to 70% of those streams. AI-generated music is a growing problem on streaming platforms. Fraudsters typically generate revenue on platforms such as Deezer by using bots to "listen" to AI-generated songs – and take the subsequent royalty payments, which become sizeable once spread across multiple tracks. The tactic aims to evade detection measures triggered by vast listening numbers for a small amount of bogus tracks.

The ability of large language models (LLMs) to utilize external tools has enabled them to tackle an increasingly diverse range of tasks. However, as the tasks become more complex and long-horizon, the intricate tool utilization process may trigger various unexpected errors. Therefore, how to effectively handle such errors, including identifying, diagnosing, and recovering from them, has emerged as a key research direction for advancing tool learning. In this work, we first extensively analyze the types of errors encountered during the function-calling process on several competitive tool evaluation benchmarks. Based on it, we introduce CRITICTOOL, a comprehensive critique evaluation benchmark specialized for tool learning. Building upon a novel evolutionary strategy for dataset construction, CRITICTOOL holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios. We conduct extensive experiments on CRITICTOOL, and validate the generalization and effectiveness of our constructed benchmark strategy. We also provide an in-depth analysis of the tool reflection ability on various LLMs, offering a new perspective on the field of tool learning in LLMs. The code is available at \href{https://github.com/Shellorley0513/CriticTool}{https://github.com/Shellorley0513/CriticTool}.

Instruction-based image editing, which aims to modify the image faithfully according to the instruction while preserving irrelevant content unchanged, has made significant progress. However, there still lacks a comprehensive metric for assessing the editing quality. Existing metrics either require high human evaluation costs, which hinder large-scale evaluation, or are adapted from other tasks and lose task-specific concerns, failing to comprehensively evaluate both instruction-based modification and preservation of irrelevant regions, resulting in biased evaluation. To tackle this, we introduce a new metric called Balancing Preservation and Modification (BPM), tailored for instruction-based image editing by explicitly disentangling the image into editing-relevant and irrelevant regions for specific consideration. We first identify and locate editing-relevant regions, followed by a two-tier process to assess editing quality: Region-Aware Judge evaluates whether the position and size of the edited region align with the instruction, and Semantic-Aware Judge further assesses the instruction content compliance within editing-relevant regions as well as content preservation within irrelevant regions, yielding comprehensive and interpretable quality assessment. Moreover, the editing-relevant region localization in BPM can be integrated into image editing approaches to improve editing quality, demonstrating its broad applicability. We verify the effectiveness of the BPM metric on comprehensive instruction-editing data, and the results show the highest alignment with human evaluation compared to existing metrics, indicating its efficacy. Code is available at: https://joyli-x.github.io/BPM/