$Cover Image$

FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Seegmiller, Parker, Mehta, Kartik, Saha, Soumya, Tao, Chenyang, Oraby, Shereen, Gupta, Arpit, Chung, Tagyoung, Bansal, Mohit, Peng, Nanyun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
by: Ferraz, Thomas Palmeira, et al.
Published: (2024)

Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
by: Chang, Haw-Shiuan, et al.
Published: (2024)

REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
by: Chang, Haw-Shiuan, et al.
Published: (2024)

DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
by: Lu, Sidi, et al.
Published: (2023)

CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization
by: Joshi, Brihi, et al.
Published: (2025)

Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance
by: Seegmiller, Parker, et al.
Published: (2026)

DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
by: Parekh, Tanmay, et al.
Published: (2025)

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
by: Chen, Justin Chih-Yao, et al.
Published: (2023)

Depth $F_1$: Improving Evaluation of Cross-Domain Text Classification by Measuring Semantic Generalizability
by: Seegmiller, Parker, et al.
Published: (2024)

Mitigating Bias for Question Answering Models by Tracking Bias Influence
by: Ma, Mingyu Derek, et al.
Published: (2023)

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?
by: He, Xuan, et al.
Published: (2024)

Fine-Tuning Qwen 2.5 3B for Realistic Movie Dialogue Generation
by: Gupta, Kartik
Published: (2025)

FLAMES: Fine-tuning LLMs to Synthesize Invariants for Smart Contract Security
by: Eshghie, Mojtaba, et al.
Published: (2025)

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
by: Huan, Maggie, et al.
Published: (2025)

DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation
by: Wang, Zun, et al.
Published: (2024)

Improving Narrative Classification and Explanation via Fine Tuned Language Models
by: Tyagi, Rishit, et al.
Published: (2025)

Knowledge-Aware Reasoning over Multimodal Semi-structured Tables
by: Mathur, Suyash Vardhan, et al.
Published: (2024)

MIDDLE EAST: SPREADING FLAMES
Published: (1955)

Learning-Based Image Compression for Machines
by: Gupta, Kartik, et al.
Published: (2024)

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
by: Khan, Zaid, et al.
Published: (2025)

Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types
by: Gatto, Joseph, et al.
Published: (2024)

DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning
by: Tu, Shangqing, et al.
Published: (2024)

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
by: Wu, Xueqing, et al.
Published: (2024)

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
by: Wadhawan, Rohan, et al.
Published: (2024)

Redefining Proactivity for Information Seeking Dialogue
by: Lee, Jing Yang, et al.
Published: (2024)

Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data
by: Li, Zijian, et al.
Published: (2025)

Branch-Solve-Merge Improves Large Language Model Evaluation and Generation
by: Saha, Swarnadeep, et al.
Published: (2023)

RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
by: Gupta, Pankaj, et al.
Published: (2026)

In-Context Learning for Preserving Patient Privacy: A Framework for Synthesizing Realistic Patient Portal Messages
by: Gatto, Joseph, et al.
Published: (2024)

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
by: Yu, Shoubin, et al.
Published: (2024)

SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning
by: Rahman, Salman, et al.
Published: (2025)

Astrophysical aspects of $^{12}$C$(p,γ)^{13}$N reaction
by: Saha, Soumya
Published: (2024)

Reliable Fine-Grained Evaluation of Natural Language Math Proofs
by: Ma, Wenjie, et al.
Published: (2025)

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
by: Xu, Yifan, et al.
Published: (2024)

Fine-Grained Self-Endorsement Improves Factuality and Reasoning
by: Wang, Ante, et al.
Published: (2024)

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
by: Sung, Yi-Lin, et al.
Published: (2023)

SHARING THE SPIRIT, FANNING THE FLAMES OF SOCIAL JUSTICE
by: Rosangela Malachias
Published: (2018)

Fine-Grained Traceability for Transparent ML Pipelines
by: Chen, Liping, et al.
Published: (2026)