arXiv Computation and Language
Voice of Reason: Reinforcement Learning for Spoken Math
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Aug 11
Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond
arXiv:2510. 19990v2 Announce Type: replace Abstract: The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving.
Hugging Face Trending Papers
Jul 22
Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models
Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language models, especially on spoken mathematical question answering tasks. One important reason is that SLMs reason over purely verbalized mathematical expressions, which are harder to interpret than symbolic text.
arXiv AI
Aug 7
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
arXiv AI
Aug 19
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning
SignalReasoner evaluates reinforcement fine‑tuning methods for the Qwen2.5‑3B‑Base language model on graduate‑level signal processing math problems from the WirelessMATHBench‑XL benchmark. Two training paradigms are compared: direct reinforcement learning with verifiable rewards, and supervised chain‑of‑thought fine‑tuning followed by domain‑specific reinforcement learning. The study benchmarks three policy optimization algorithms—GRPO, GSPO, and GMPO—to determine if domain‑aware chain‑of‑thought initialization improves performance, achieving a best accuracy of 39.12% versus 12.37% for the untrained base model.
arXiv Machine Learning
Jul 17
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
arXiv:2607. 14895v1 Announce Type: new Abstract: Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding.
arXiv AI
Sep 30
Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
arXiv:2609.37818v1 Announce Type: cross Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguis...