arXiv Computation and Language

Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning

The paper introduces a data‑centric pipeline for post‑training language models on financial reasoning tasks. It mines open‑source reasoning traces, distills financial instruction data, and generates knowledge‑graph‑guided question‑answer pairs, then filters examples with lightweight classifiers and applies reinforcement learning with rule‑based verifiers. Experiments on FINESSE‑Bench show that retention‑aware adaptation—self‑distilled fine‑tuning and model merging—outperforms ordinary supervised fine‑tuning, improving accuracy by up to 3.0 points and avoiding regressions.

arXiv AI
Sep 10

ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

ASDA (Automated Skill Distillation and Adaptation) is a framework that improves large language models on financial reasoning tasks without fine‑tuning. It works by having a teacher model analyze a student’s failures, cluster errors, and generate structured skill artifacts—reasoning procedures, code templates, and worked examples—that are injected during inference. On the FAMMA benchmark, ASDA boosts arithmetic reasoning by up to 17.33% and non‑arithmetic reasoning by 5.95%, outperforming existing training‑free methods.

By Tik Yu Yim, Wenting Tan, Sum Yee Chan, Tak-Wah Lam, Siu Ming Yiu
Hugging Face Trending Papers
Jun 17

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.

arXiv Machine Learning
Aug 12

Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

arXiv:2604. 02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers.

By Yiyang Shen, Lifu Tu, Weiran Wang
arXiv Computation and Language
Oct 15

QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models

arXiv:2601.08689v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong capabilities in finance-oriented question answering, yet their evaluation on professional quantitati...

By Zhaolu Kang, Junhao Gong, Wenqing Hu, Yingjie He, Kehan Jiang, Leqi Zheng, Shuo Yin, Zhicheng Fang, Chunlei Meng, Eric Hanchen Jiang, Yunfei Feng, Yitong Leng, Junfan Zhu, Xiaoyou Chen, Xi Yang, Richeng Xuan
arXiv AI
Aug 25

Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data

arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reason...

By Yinhao Tang, Youqing Fang, Yanan Sun, Jiangning Liu, Ziyi Wang, Xun Zhao, Weiming Zhang, Bin Liu, Kuikun Liu, Wenwei Zhang, Kai Chen
arXiv AI
Aug 11

FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks

arXiv:2604. 10015v3 Announce Type: replace Abstract: Recent studies demonstrate that tool-calling capability enables large language models (LLMs) to interact with external environments for long-horizon financial tasks.

By Yupeng Cao, Haohang Li, Weijin Liu, Wenbo Cao, Anke Xu, Lingfei Qian, Xueqing Peng, Minxue Tang, Zhiyuan Yao, Jimin Huang, K. P. Subbalakshmi, Zining Zhu, Jordan W. Suchow, Yangyang Yu
arXiv AI
Jun 26

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.

By Qiaobo Hao, Yangqian Wu, Shunyi Wang, Zhongjian Zhang, Ziqun Li, Yayin He, Muqing Li, Chen Zhong
arXiv Machine Learning
Sep 24

Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning

The paper introduces RECAP, a redundancy-aware credit assignment method that improves reasoning efficiency in large language models by assigning credit to each reasoning step based on its downstream role and contribution to the correct answer. RECAP uses a semantic dependency graph to measure structural responsibility and evaluates step efficacy via changes in gold-answer log-likelihood, enabling step-specific updates without requiring a separate reward model or concise trajectories. Experiments on two 7B models across four mathematical reasoning benchmarks show that RECAP enhances the accuracy-efficiency trade-off, boosting pass@1 by 2.0–3.7 percentage points while cutting reasoning tokens by 8–31% compared to GRPO.

By Yuqing Zhou, Hong Wang, Manqing Mao, Zhuoer Wang, Samson Koelle, Jie Yuan, Yanjun Lin, James Feng, Nikki Lijing Kuang, Ziwei Zhu, Wei Niu