arXiv AI September 10, 2026 By Tik Yu Yim, Wenting Tan, Sum Yee Chan, Tak-Wah Lam, Siu Ming Yiu

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 12

V-FiLLM: Verified Financial LLM Reasoning Benchmark

arXiv:2608. 11047v1 Announce Type: new Abstract: While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains comparatively less explored.

By Alicia Larsen, Victoire Laurent, Aulia Kharis Rakhamsari, Lara Turgut, Nino Antulov-Fantulin

llms fine-tuning benchmarks safety

arXiv Computation and Language

Sep 10

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.

By Zhirayr Hayrapetyan, Andrei Kalmykov, Denis Kokosinskii, Dmitry Stanishevskii, Dmitry Zmitrovich

llms reinforcement-learning fine-tuning efficiency

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.

By Yu-Du Feng, Niels M\"undler-Sasahara, Mark Vero, Martin Vechev

llms nlp reinforcement-learning fine-tuning

arXiv AI

Jun 30

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.

By Xiaojun Wu, Xiaoguang Jiang, Huiyang Li, Jucai Zhai, Dengfeng Liu, Qiaobo Hao, Huang Liu, Zhiguo Yang, Ji Xie, Ninglun Gu, Jin Yang, Kailai Zhang, Yelun Bao, Jun Wang

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jul 7

Agentic Retrieval-Augmented Generation for Financial Document Question Answering

arXiv:2605. 05409v2 Announce Type: replace Abstract: Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scattered across corporate filings.

By Yang Shu, Yingmin Liu, Zequn Xie

llms rag agents nlp benchmarks

arXiv AI

Jul 24

Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility

arXiv:2607. 20440v1 Announce Type: cross Abstract: Proprietary large language models (LLMs) entail substantial intellectual and financial investment, making them valuable intellectual property (IP).

By Fan Li, Mengting Pan, Sijia Xu, Xiaoyang Wang, Chen Chen, Wenjie Zhang

llms efficiency benchmarks

One email a morning, machine-written

Related stories

V-FiLLM: Verified Financial LLM Reasoning Benchmark

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

Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

Agentic Retrieval-Augmented Generation for Financial Document Question Answering

Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility