We study leveraging adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval.Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial query.While existing reasoning-based reranker pipelines attempt to surface these documents in ranking, they suffer from bounded recall.Naive solution with adaptive retrieval into these pipelines often leads to planning error propagation.To address this, we propose REPAIR, a framework that bridges this gap by repurposing reasoning plans as dense feedback signals for adaptive retrieval.Our key distinction is enabling mid-course correction during reranking through selective adaptive retrieval, retrieving documents that support the pivotal plan.Experimental results on reasoning-intensive retrieval and complex QA tasks demonstrate that our method outperforms existing baselines by 5.6%pt.

Dohyeon Lee, Jongyoon Kim, Jihyuk Kim, Seung-won Hwang, Joonsuk Park. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Despite advancements in Large Language Models (LLMs), many complex tasks are not easily solved in a single inference step, requiring the use of agentic LLMs in interactive environments.However, agentic LLMs suffer from a phenomenon known as reasoning derailment, due to the indiscriminate incorporation of observations from partially observable environments.We introduce QuBE, a method that enhances agents' focus on task-relevant contexts, by constructing a belief state via question answering.We validate QuBE through experiments in two agentic LLM scenarios with partial observability: 1) a canonical interactive decision-making scenario using text-based game engines, and 2) an interactive retrievalaugmented generation (RAG) scenario using search engines.In the ALFWorld text-based game, QuBE outperforms established baselines by substantial margins, and in the search engine scenario, it achieves marked improvements on the BEIR zero-shot retrieval benchmark.The results demonstrate that QuBE significantly mitigates reasoning derailment, refining the decision-making process of LLM agents in partially observed environments.1

This paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval.The biencoder, separately encoding a query and a document as a single vector, is favored for high efficiency in large-scale information retrieval, compared to more effective but complex architectures.To combine the strength of the two, the multi-vector representation of documents for bi-encoder, such as ColBERT preserving all token embeddings, has been widely adopted.Our contribution is to reduce the size of the multi-vector representation, without compromising the effectiveness, supervised by query logs.Our proposed solution decreases the latency and the memory footprint, up to 8-and 3fold, validated on MSMARCO and real-world search query logs 1 .

Deep learning for Information Retrieval (IR) requires a large amount of high-quality querydocument relevance labels, but such labels are inherently sparse.Label smoothing redistributes some observed probability mass over unobserved instances, often uniformly, uninformed of the true distribution.In contrast, we propose knowledge distillation for informed labeling, without incurring high computation overheads at evaluation time.Our contribution is designing a simple but efficient teacher model which utilizes collective knowledge, to outperform state-of-thearts distilled from a more complex teacher model.Specifically, we train up to ×8 faster than the state-of-the-art teacher, while distilling the rankings better.Our code is publicly available at https://github.com/ jihyukkim-nlp/CollectiveKD.

This paper studies the keyphrase generation (KG) task for scenarios where structure plays an important role.For example, a scientific publication consists of a short title and a long body, where the title can be used for de-emphasizing unimportant details in the body.Similarly, for short social media posts (e.g., tweets), scarce context can be augmented from titles, though often missing.Our contribution is generating/augmenting structure then encoding these information, using existing keyphrases of other documents, complementing missing/incomplete titles.Specifically, we first extend the given document with related but absent keyphrases from existing keyphrases, to augment missing contexts (generating structure), and then, build a graph of keyphrases and the given document, to obtain structure-aware representation of the augmented text (encoding structure).Our empirical results validate that our proposed structure augmentation and structure-aware encoding can improve KG for both scenarios, outperforming the state-of-the-art 1 .

We study keyphrase extraction (KPE) from Web documents. Our key contribution is encoding Web documents to leverage structure, such as title or anchors, by building a graph of words representing both (a) position-based proximity and (b) structural relations. We evaluate KPE performance on real-world search engine NAVER and human-annotated KPE benchmarks, and ours outperforms state-of-the-arts in both tasks.