With the release of R1, a publicly available large reasoning model (LRM), researchers commonly train new LRMs by training language models on R1’s long chain-of-thought (CoT) inferences. While prior works show that LRMs’ capabilities can be reproduced through direct distillation, the continued reliance on the existing models (e.g., R1) remains a critical limitation in advancing the field.As a first step toward independent LRM development, this paper explores the possibility of constructing a long CoT dataset with LLMs that are not trained for inference-time scaling.To this end, we present the Long CoT Collection, a dataset of 100K CoT rationales annotated using existing short CoT LLMs. We develop a pipeline that induces o1’s novel reasoning strategies into short CoT LLMs, enabling them to think longer and introducing controllability over the thought budget to better manage the overthinking problem.Our extensive analyses validate that our dataset achieves quality comparable to—or slightly below—R1. Furthermore, our experiments demonstrate that training on our dataset not only strengthens general reasoning skills, but also provides a strong foundation for reinforcement learning—models initialized on our data achieve 2-3x larger gains with RLVR. We make the codes, datasets, and models publicly available at LINK.

Targeting long-form question-answering, chain-of-query (CoQ) has been studied, integrating chain-of-thought (CoT) with retrieval-augmented generation. CoQ answers the complex question step-by-step, through simpler subquestions (SQs) from which relevant knowledge is retrieved. By doing so, CoQ aims to improve the answer comprehensiveness and verifiability, at the expense of latency. Our first contribution is showing that the chaining often incurs harmful effects on both objectives, and SQs left unverified often fail to answer the given question. Second, we propose a better alternative to CoQ, union-of-query which adopts a factored approach to break the harmful chain. Finally, we propose to verify SQs before answers, by fine-tuning the SQ generator using verified SQs and introducing a selector verifying SQs in test time. Employing vicuna-13b, our approach, denoted by FaVe (short for Factored and Verified search), even outperforms ChatGPT baselines while maintaining efficiency.

Prompt optimization (PO) generates prompts to guide Large Language Models (LLMs) in performing tasks. Existing methods, such as PromptAgent, rely on a single static prompt, which struggles with disjoint cases in complex tasks. Although MoP uses multiple prompts, it fails to account for variations in task complexity. Inspired by programmatic control flow, we introduce a nested if-else structure to address both varying similarities and complexities across diverse cases. We propose Tree-of-Prompts (ToP), which implements this structure by recursively expanding child prompts from a parent prompt. Sibling prompts tackle disjoint cases while inheriting shared similarities from their parent, and handle cases more complex than the parent. Evaluated on Gorilla (understanding), MATH (reasoning), and a subset of BBH benchmarks, ToP outperforms PromptAgent and MoP, with improvements of 1.4% and 4.6% over PromptAgent and 3.2% and 4.5% over MoP, when tested with GPT-4o-mini and Llama 3.2-3B, respectively.

Neural retrieval models have emerged as an effective tool for information retrieval, but their performance suffers when there is a domain shift between training and test data distributions. Recent work aims to construct pseudo-training data for the target domain by generating domain-adapted pseudo-queries using large language models (LLMs). However, we identifies that LLMs exhibit a “seen term bias” where the generated pseudo-queries fail to include relevant “unseen” terms as expected for domain adaptation purposes. To address this limitation, we propose to improve the term recall of unseen query terms, by using term-level Retrieval-Augmented Generation (tRAG). Specifically, unlike existing document-level RAG, we propose to generate domain-specific keywords from all documents in the corpus, including those unseen in any individual document. To filter hallucination, generated keywords are retrieved and reranked, leveraging relevance feedback from both retrievers and LLMs. Experiments on the BEIR benchmark show tRAG significantly improves recall for unseen terms by 10.6% and outperforms LLM and retrieval-augmented generation baselines on overall retrieval performance.

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 retrieval-augmented 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.

Zero-shot retrieval tasks such as the BEIR benchmark reveal out-of-domain generalization as a key weakness of high-performance dense retrievers. As a solution, domain adaptation for dense retrievers has been actively studied. A notable approach is synthesizing domain-specific data, by generating pseudo queries (PQ), for fine-tuning with domain-specific relevance between PQ and documents. Our contribution is showing that key biases can cause sampled PQ to be irrelevant, negatively contributing to generalization. We propose to preempt their generation, by dividing the generation into simpler subtasks, of generating relevance explanations and guiding the generation to avoid negative generalization. Experiment results show that our proposed approach is more robust to domain shifts, validated on challenging BEIR zero-shot retrieval tasks.

Instructional videos make learning knowledge more efficient, by providing a detailed multimodal context of each procedure in instruction.A unique challenge posed by instructional videos is key-object degeneracy, where any single modality fails to sufficiently capture the key objects referred to in the procedure. For machine systems, such degeneracy can disturb the performance of a downstream task such as dense video captioning, leading to the generation of incorrect captions omitting key objects. To repair degeneracy, we propose a retrieval-based framework to augment the model representations in the presence of such key-object degeneracy. We validate the effectiveness and generalizability of our proposed framework over baselines using modalities with key-object degeneracy.

This paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval. The bi-encoder, 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 3-fold, validated on MSMARCO and real-world search query logs.

Deep learning for Information Retrieval (IR) requires a large amount of high-quality query-document 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-the-arts 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 (, tweets), scarce context can be augmented from titles, though often missing. Our contribution is generating/augmenting structure then injecting these information in the encoding, using existing keyphrases of other documents, complementing missing/incomplete titles. We propose novel structure-augmented document encoding approaches that consist of the following two phases: The first phase, generating structure, extends the given document with related but absent keyphrases, augmenting missing context. The second phase, encoding structure, builds a graph of keyphrases and the given document to obtain the structure-aware representation of the augmented text. Our empirical results validate that our proposed structure augmentation and augmentation-aware encoding/decoding can improve KG for both scenarios, outperforming the state-of-the-art.