AIConfPaper
← Search

Soji Adeshina

5 accepted papers

2026

Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier

Yegor Denisov-Blanch, Joshua Kazdan, Jessica Chudnovsky, Rylan Schaeffer, Sheng Guan, Soji Adeshina +1
ICML 2026poster

Pass@$k$ and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect candidates can be filtered reliably. This raises a natural question: can we similarly scale compute to elicit gains in tr…

Cited by 0Source ↗Scholar ↗
2025

BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering

Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han, Qi Zhu, Ian Robinson +3
EMNLP 2025

Knowledge graph question answering (KGQA) presents significant challenges due to the structural and semantic variations across input graphs. Existing works rely on Large Language Model (LLM) agents for graph traversal and retrieval; an approach that is sensitive to traversal initialization, as it is

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases

Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis +2
ACL 2025long

Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions?Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; whi…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

NetInfoF Framework: Measuring and Exploiting Network Usable Information

Meng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang song, Soji Adeshina +2
ICLR 2024spotlight

Given a node-attributed graph, and a graph task (link prediction or node classification), can we tell if a graph neural network (GNN) will perform well? More specifically, do the graph structure and the node features carry enough usable information for the task? Our goals are (1) to develop a fast t…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2022

Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features

Jiuhai Chen, Jonas Mueller, Vassilis N. Ioannidis, Soji Adeshina, Yangkun Wang, Tom Goldstein +1
ICLR 2022spotlight

Many practical modeling tasks require making predictions using tabular data composed of heterogeneous feature types (e.g., text-based, categorical, continuous, etc.). In this setting boosted decision trees and related ensembling techniques generally dominate real-world applications involving iid tr…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗