arXiv AI
Answer Probing-Guided Search for Diverse Solution Exploration of LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 21
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.
arXiv AI
Jul 28
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv:2509. 03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth correctness can be automatically evaluated.
arXiv AI
Oct 19
Diverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for Enhancing RL Exploration
The paper introduces EquivAug, a data augmentation framework that applies symbolic equivalence transformations to chain-of-thought (CoT) solutions, generating diverse yet provably correct reasoning paths for supervised fine-tuning (SFT). By converting CoT solutions into formal symbolic representations, applying equivalence transformations, and reconstructing natural-language explanations, EquivAug produces training data that varies in reasoning steps rather than surface-level lexical differences. Experiments on GSM8K and FOLIO show that EquivAug consistently achieves the highest reasoning path diversity after SFT and the strongest accuracy after GRPO, establishing a positive correlation between CoT diversity during SFT and downstream reinforcement learning with verifiable rewards (RLVR) performance.
arXiv AI
Aug 12
From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models
arXiv:2608. 10444v1 Announce Type: cross Abstract: Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains.
arXiv AI
Jul 15
CANDI: Contextual Alignment for Niche Domains Question Answering
arXiv:2607. 11891v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) in specialized domains like medical diagnostics and financial advisory necessitates evaluating capabilities beyond general knowledge.
arXiv Computation and Language
Oct 5
BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions
BioMol-MQA is a new question‑answering dataset focused on polypharmacy that combines a multimodal knowledge graph—containing both text and molecular structure—with challenging questions designed to test large language models’ ability to retrieve and reason over this diverse information. The dataset highlights the limitations of current retrieval‑augmented generation systems, which typically handle only single‑modality text, by demonstrating that existing LLMs perform poorly unless provided with the necessary multimodal background data. This underscores the need for more robust RAG frameworks capable of integrating multiple data types for accurate responses.