Long-context question answering over narrative documents remains challenging because many questions require reconstructing event sequences while preserving local contextual flow under limited context budgets. Existing retrieval-augmented generation (RAG) methods typically retrieve document snippets independently, which can fragment narratives and harm temporal dependencies. We propose ChronoRAG, a retrieval framework for narrative question answering that first converts sequential document chunks into concise relation descriptions and then retrieves relevant units together with their adjacent chronological context. This design preserves retrieval precision while providing the generator with coherent local narrative structure. Experiments on NarrativeQA and GutenQA show that ChronoRAG improves performance on NarrativeQA and remains competitive on GutenQA, with particularly strong gains on questions that require chronology-sensitive context. These results suggest that explicitly modeling local event order is a useful retrieval signal for narrative question answering.

Given a multi-turn conversational context and a raw user query, the goal of Conversational Query Reformulation (CQR) is to transform the query into a de-contextualized form that maximizes retrieval effectiveness for a downstream passage retriever. Conversational search seeks to retrieve relevant passages for the given questions in a conversational question answering system. Conversational Query Reformulation (CQR) improves conversational search by refining the original queries into de-contextualized forms to address issues such as omissions and coreferences. Previous CQR methods focus on imitating human-written queries, which may not always yield meaningful search results for the retriever. In this paper, we introduce GuideCQR, a framework that refines queries for CQR by leveraging key information from the initially retrieved documents. Specifically, GuideCQR extracts keywords and generates expected answers from the retrieved documents, then unifies them with the queries after filtering to add useful information that enhances the search process. Experimental results demonstrate that our proposed method achieves state-of-the-art performance across multiple datasets, outperforming previous CQR methods. Specifically, GuideCQR achieves MRR gains of 5.4% over LLM4CS on CAsT-19 and NDCG@3 gains of 29.2% on QReCC, and consistently improves retrieval across CAsT-19, CAsT-20, and QReCC benchmarks, demonstrating strong adaptability to various query types including human-rewritten queries. Additionally, we show that GuideCQR can get additional performance gains in conversational search using various types of queries, even for queries written by humans.