arXiv AI
ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 19
The Significance of Style Diversity in Annotation-Free Synthetic Data Generation
arXiv:2606. 20400v1 Announce Type: new Abstract: Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings.
arXiv Computation and Language
Sep 2
Evaluating Style-Personalized Text Generation: Challenges and Directions
The paper "Evaluating Style-Personalized Text Generation: Challenges and Directions" examines the difficulties of assessing text that is tailored to individual users’ styles. It critiques common metrics such as BLEU, embeddings, and LLM-as-judges, and introduces a style discrimination benchmark covering domain discrimination, authorship attribution, and LLM-generated personalized versus non-personalized discrimination across eight writing tasks. The study finds that ensembles of diverse evaluation metrics outperform single-evaluator approaches and offers guidance for reliable assessment of style-personalized generation.
arXiv Machine Learning
Sep 18
Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations
The paper introduces a training‑free method for uncovering prompt‑conditional stylistic axes in large language models (LLMs). By repeatedly sampling completions of a single prompt at high temperature and applying Principal Component Analysis (PCA) to the pooled hidden activations, the authors automatically label the resulting axes using the extreme (pole) generations. Validation against 245 human‑elicited stylistic annotations shows that, for the Qwen‑3.5‑4B‑Instruct model, the top two axes align with human dimensions with 72.8% precision and 43.6% macro‑recall, and 75.6% of validity ratings confirm the axes’ polar generations, while other models exhibit varying degrees of discoverability.
arXiv Computation and Language
5d ago
Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech
The paper introduces Speech-Rewarded Style Planning (SRSP), a method that trains a text-based style planner using a frozen downstream TTS model. SRSP generates candidate style instructions from dialogue history and response text, optimizing them with group-relative policy optimization (GRPO) where the reward is the teacher‑forced likelihood of target speech tokens. Experiments on an English subset of the ISCSLP 2026 CoT‑TTS corpus show that SRSP outperforms baseline LLM and target‑audio‑informed captioning approaches in speech‑style and emotion similarity, mel‑cepstral distortion, and contextual appropriateness. "whyItMatters":"The study demonstrates a more effective way to align natural‑language style descriptions with actual acoustic output, improving controllability and fidelity in conversational text‑to‑speech systems."
arXiv AI
Jul 3
HAL: Inducing Human-likeness in LLMs with Alignment
arXiv:2601. 02813v3 Announce Type: replace Abstract: Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize.
arXiv Machine Learning
5d ago
Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners
The paper presents Conversational Voice Aesthetic Model (CVAM), a speech large language model that describes voice aesthetics in conversational contexts. CVAM predicts nine categorical attributes such as gender, pitch, pacing, emotion, and delivery, and is trained on human-annotated data from the CANDOR corpus. Experiments show that CVAM aligns better with human listeners than Gemini 3.1 Pro and other open‑source speech LLMs, demonstrating the value of grounding voice aesthetics in human perception.