5 papers
SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
Daeyong Kwon, Soyoung Yoon, Seung-won Hwang
Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning. We propose SA…
On Listwise Reranking for Corpus Feedback
Soyoung Yoon, Jongho Kim, Daeyong Kwon +2
Reranker improves retrieval performance by capturing document interactions. At one extreme, graph-aware adaptive retrieval (GAR) represents an information-rich regime, requiring a…
AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
Soyoung Yoon, Gyuwan Kim, Gyu-Hwung Cho +1
Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long c…
RoToR: Towards More Reliable Responses for Order-Invariant Inputs
Soyoung Yoon, Dongha Ahn, Youngwon Lee +3
Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have b…
Analyzing the Effectiveness of Listwise Reranking with Positional Invariance on Temporal Generalizability
Soyoung Yoon, Jongyoon Kim, Seung-won Hwang
This working note outlines our participation in the retrieval task at CLEF 2024. We highlight the considerable gap between studying retrieval performance on static knowledge docume…