Benchmarking Information Retrieval Models on Complex Retrieval Tasks

Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contrast, have not yet seen such capable general-purpose models emerge. To achieve this goal, retrieval models must be able to perform complex retrieval tasks, where queries contain multiple parts, constraints, or requirements in natural language. These tasks represent a natural progression from the simple, single-aspect queries that are used in the vast majority of existing, commonly used evaluation sets. Complex queries naturally arise as people expect search systems to handle more specific and often ambitious information requests, as is demonstrated by how people use LLM-based information systems. Despite the growing desire for retrieval models to expand their capabilities in complex retrieval tasks, there exist limited resources to assess the ability of retrieval models on a comprehensive set of diverse complex tasks. The few resources that do exist feature a limited scope and often lack realistic settings making it hard to know the true capabilities of retrieval models on complex real-world retrieval tasks. To address this shortcoming and spur innovation in next-generation retrieval models, we construct a diverse and realistic set of complex retrieval tasks and benchmark a representative set of state-of-the-art retrieval models. Additionally, we explore the impact of LLM-based query expansion and rewriting on retrieval quality. Our results show that even the best models struggle to produce high-quality retrieval results with the highest average nDCG@10 of only 0.346 and R@100 of only 0.587 across all tasks. Although LLM augmentation can help weaker models, the strongest model has decreased performance across all metrics with all rewriting techniques.

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models

Aligning LLMs with user preferences is crucial for real-world use but often requires costly fine-tuning or expensive inference, forcing trade-offs between alignment quality and computational cost. Existing inference-time methods typically ignore this balance, focusing solely on the optimized policy's performance. We propose HIA (Heuristic-Guided Inference-time Alignment), a tuning-free, black-box-compatible approach that uses a lightweight prompt optimizer, heuristic reward models, and two-stage filtering to reduce inference calls while preserving alignment quality. On real-world prompt datasets, HelpSteer and ComPRed, HIA outperforms best-of-N sampling, beam search, and greedy search baselines in multi-objective, goal-conditioned tasks under the same inference budget. We also find that HIA is effective under low-inference budgets with as little as one or two response queries, offering a practical solution for scalable, personalized LLM deployment.

CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-Training

This paper presents mRAG, a multi-agent retrieval-augmented generation (RAG) framework composed of specialized agents for subtasks such as planning, searching, reasoning, and coordination. Our system uses a self-training paradigm with reward-guided trajectory sampling to optimize inter-agent collaboration and enhance response generation. Evaluated on DataMorgana-derived datasets during the SIGIR 2025 LiveRAG competition, mRAG outperforms conventional RAG baselines. We further analyze competition outcomes and showcase the framework's strengths with case studies, demonstrating its efficacy for complex, real-world RAG tasks.

Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?

While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and development. To address this gap, we formulate the task of selecting pre-training checkpoints to maximize downstream fine-tuning performance as a pairwise classification problem: predicting which of two LLMs, differing in their pre-training, will perform better after supervised fine-tuning (SFT). We construct a dataset using 50 1B parameter LLM variants with systematically varied pre-training configurations, e.g., objectives or data, and evaluate them on diverse downstream tasks after SFT. We first conduct a study and demonstrate that the conventional perplexity is a misleading indicator. As such, we introduce novel unsupervised and supervised proxy metrics derived from pre-training that successfully reduce the relative performance prediction error rate by over 50%. Despite the inherent complexity of this task, we demonstrate the practical utility of our proposed proxies in specific scenarios, paving the way for more efficient design of pre-training schemes optimized for various downstream tasks.

Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generation

This paper studies the limitations of (retrieval-augmented) large language models (LLMs) in generating diverse and comprehensive responses, and introduces the Plan-and-Refine (P&R) framework based on a two phase system design. In the global exploration phase, P&R generates a diverse set of plans for the given input, where each plan consists of a list of diverse query aspects with corresponding additional descriptions. This phase is followed by a local exploitation phase that generates a response proposal for the input query conditioned on each plan and iteratively refines the proposal for improving the proposal quality. Finally, a reward model is employed to select the proposal with the highest factuality and coverage. We conduct our experiments based on the ICAT evaluation methodology--a recent approach for answer factuality and comprehensiveness evaluation. Experiments on the two diverse information seeking benchmarks adopted from non-factoid question answering and TREC search result diversification tasks demonstrate that P&R significantly outperforms baselines, achieving up to a 13.1% improvement on the ANTIQUE dataset and a 15.41% improvement on the TREC dataset. Furthermore, a smaller scale user study confirms the substantial efficacy of the P&R framework.

Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking

We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human annotations or large black-box language models, our methodology leverages web data and a teacher LLM to automatically generate high-quality training examples with relevance explanations. By framing document ranking as a reinforcement learning problem and incentivizing explicit reasoning capabilities, we train a compact 3B parameter language model that achieves state-of-the-art performance on the BRIGHT benchmark. Our model ranks third on the leaderboard while using substantially fewer parameters than other approaches, outperforming models that are over 20 times larger. Through extensive experiments, we demonstrate that generating explanations during inference, rather than directly predicting relevance scores, enables more effective reasoning with smaller language models. The self-supervised nature of our method offers a scalable and interpretable solution for modern information retrieval systems.

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Retrieval augmentation and tool-use training approaches where a search engine is treated as a tool lack complex multi-turn retrieval flexibility or require large-scale supervised data. Prompting advanced LLMs with reasoning capabilities during inference to use search engines is not optimal, since the LLM does not learn how to optimally interact with the search engine. This paper introduces Search-R1, an extension of the DeepSeek-R1 model where the LLM learns -- solely through reinforcement learning (RL) -- to autonomously generate (multiple) search queries during step-by-step reasoning with real-time retrieval. Search-R1 optimizes LLM rollouts with multi-turn search interactions, leveraging retrieved token masking for stable RL training and a simple outcome-based reward function. Experiments on seven question-answering datasets show that Search-R1 improves performance by 26% (Qwen2.5-7B), 21% (Qwen2.5-3B), and 10% (LLaMA3.2-3B) over SOTA baselines. This paper further provides empirical insights into RL optimization methods, LLM choices, and response length dynamics in retrieval-augmented reasoning. The code and model checkpoints are available at https://github.com/PeterGriffinJin/Search-R1.

Personalized Generation In Large Model Era: A Survey

In the era of large models, content generation is gradually shifting to Personalized Generation (PGen), tailoring content to individual preferences and needs. This paper presents the first comprehensive survey on PGen, investigating existing research in this rapidly growing field. We conceptualize PGen from a unified perspective, systematically formalizing its key components, core objectives, and abstract workflows. Based on this unified perspective, we propose a multi-level taxonomy, offering an in-depth review of technical advancements, commonly used datasets, and evaluation metrics across multiple modalities, personalized contexts, and tasks. Moreover, we envision the potential applications of PGen and highlight open challenges and promising directions for future exploration. By bridging PGen research across multiple modalities, this survey serves as a valuable resource for fostering knowledge sharing and interdisciplinary collaboration, ultimately contributing to a more personalized digital landscape.

Scaling Sparse and Dense Retrieval in Decoder-Only LLMs

Scaling large language models (LLMs) has shown great potential for improving retrieval model performance; however, previous studies have mainly focused on dense retrieval trained with contrastive loss (CL), neglecting the scaling behavior of other retrieval paradigms and optimization techniques, such as sparse retrieval and knowledge distillation (KD). In this work, we conduct a systematic comparative study on how different retrieval paradigms (sparse vs. dense) and fine-tuning objectives (CL vs. KD vs. their combination) affect retrieval performance across different model scales. Using MSMARCO passages as the training dataset, decoder-only LLMs (Llama-3 series: 1B, 3B, 8B), and a fixed compute budget, we evaluate various training configurations on both in-domain (MSMARCO, TREC DL) and out-of-domain (BEIR) benchmarks. Our key findings reveal that: (1) Scaling behaviors emerge clearly only with CL, where larger models achieve significant performance gains, whereas KD-trained models show minimal improvement, performing similarly across the 1B, 3B, and 8B scales. (2) Sparse retrieval models consistently outperform dense retrieval across both in-domain (MSMARCO, TREC DL) and out-of-domain (BEIR) benchmarks, and they demonstrate greater robustness to imperfect supervised signals. (3) We successfully scale sparse retrieval models with the combination of CL and KD losses at 8B scale, achieving state-of-the-art (SOTA) results in all evaluation sets.

Open-Ended and Knowledge-Intensive Video Question Answering

Video question answering that requires external knowledge beyond the visual content remains a significant challenge in AI systems. While models can effectively answer questions based on direct visual observations, they often falter when faced with questions requiring broader contextual knowledge. To address this limitation, we investigate knowledge-intensive video question answering (KI-VideoQA) through the lens of multi-modal retrieval-augmented generation, with a particular focus on handling open-ended questions rather than just multiple-choice formats. Our comprehensive analysis examines various retrieval augmentation approaches using cutting-edge retrieval and vision language models, testing both zero-shot and fine-tuned configurations. We investigate several critical dimensions: the interplay between different information sources and modalities, strategies for integrating diverse multi-modal contexts, and the dynamics between query formulation and retrieval result utilization. Our findings reveal that while retrieval augmentation shows promise in improving model performance, its success is heavily dependent on the chosen modality and retrieval methodology. The study also highlights the critical role of query construction and retrieval depth optimization in effective knowledge integration. Through our proposed approach, we achieve a substantial 17.5% improvement in accuracy on multiple choice questions in the KnowIT VQA dataset, establishing new state-of-the-art performance levels.