Small language models need strong verifiers to self-correct reasoning

Y Zhang, M Khalifa, L Logeswaran, J Kim… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Self-correction has emerged as a promising solution to boost the reasoning performance of
large language models (LLMs), where LLMs refine their solutions using self-generated …

TRACE the evidence: Constructing knowledge-grounded reasoning chains for retrieval-augmented generation

J Fang, Z Meng, C Macdonald - arxiv preprint arxiv:2406.11460, 2024‏ - arxiv.org
Retrieval-augmented generation (RAG) offers an effective approach for addressing question
answering (QA) tasks. However, the imperfections of the retrievers in RAG models often …

Graph-constrained reasoning: Faithful reasoning on knowledge graphs with large language models

L Luo, Z Zhao, C Gong, G Haffari, S Pan - arxiv preprint arxiv:2410.13080, 2024‏ - arxiv.org
Large language models (LLMs) have demonstrated impressive reasoning abilities, but they
still struggle with faithful reasoning due to knowledge gaps and hallucinations. To address …

Demystifying chains, trees, and graphs of thoughts

M Besta, F Memedi, Z Zhang, R Gerstenberger… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The field of natural language processing (NLP) has witnessed significant progress in recent
years, with a notable focus on improving large language models'(LLM) performance through …

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

J Wu, X Li, R Wang, Y **a, Y **ong, J Wang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Offline evaluation of LLMs is crucial in understanding their capacities, though current
methods remain underexplored in existing research. In this work, we focus on the offline …

Confidence Improves Self-Consistency in LLMs

A Taubenfeld, T Sheffer, E Ofek, A Feder… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling
diverse reasoning paths and selecting the most frequent answer. However, it is …

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

F Shiri, XY Guo, MG Far, X Yu, G Haffari… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large Multimodal Models (LMMs) have achieved strong performance across a range of
vision and language tasks. However, their spatial reasoning capabilities are under …

[PDF][PDF] Knowledge Graph and Large Language Model Co-learning via Structure-oriented Retrieval Augmented Generation

C Yang, R Xu, L Luo, S Pan‏ - cs.emory.edu
Recent years have witnessed major technical breakthroughs in AI–facilitated by tremendous
data and high-performance computers, large language models (LLMs) have brought …