Logical reasoning remains a major challenge for large language models (LLMs), particularly on structured problems that require precise constraint tracking, consistency preservation, and multi-step deduction. This challenge is especially acute for small-scale LLMs, which are more prone to producing inconsistent, redunda...
Muhammad Asif Ali, Wen-Qing Wang, Huan Wang et al.· 0 citations
S PRING uses SMT solver as a training-time verifier of intermediate reasoning steps to provide process-level supervision and introduces the notion of a novel reasoning step, namely, a step that is logically valid, consistent with the evolving reasoning state, and not already implied by previously accepted non-contradic...
Muhammad Asif Ali, Wen-Qing Wang, Huan Wang et al.· 0 citations
We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcement learning using Group Relative Policy Optimization (GRPO), and deployed in FP8 for production. Koa is trained only on public and synthetically generated data, and speci...
Zi-Xiang Chen, Su-Feng Niu, Ying-Chieh Liu et al.· 0 citations
Random Attention keeps the prompt and evicts uniformly at random within each attention head, computing no score at all; across four models and six reasoning tasks, it matches the strongest baseline in task performance while delivering 32-43% higher throughput than that method when deployed with vLLM.
Heng-Yi Wang, Jie-Lin Qiu, Wenting Zhao et al.· 0 citations
It is suggested that inference-time harness design is an important complement to conventional training-time distillation, enabling strong models to transfer cognitive structure to weaker models without retraining.
Cheng Qian, Wenting Zhao, Liang-Wei Yang et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
