CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering

Retrieval-augmented generation (RAG) has become a key paradigm for knowledge-intensive question answering. However, existing multi-hop RAG systems remain inefficient, as they alternate between retrieval and reasoning at each step, resulting in repeated LLM calls, high token consumption, and unstable entity grounding across hops. We propose CompactRAG, a simple yet effective framework that decouples offline corpus restructuring from online reasoning. In the offline stage, an LLM reads the corpus once and converts it into an atomic QA knowledge base, which represents knowledge as minimal, fine-grained question-answer pairs. In the online stage, complex queries are decomposed and carefully rewritten to preserve entity consistency, and are resolved through dense retrieval followed by RoBERTa-based answer extraction. Notably, during inference, the LLM is invoked only twice in total - once for sub-question decomposition and once for final answer synthesis - regardless of the number of reasoning hops. Experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue demonstrate that CompactRAG achieves competitive accuracy while substantially reducing token consumption compared to iterative RAG baselines, highlighting a cost-efficient and practical approach to multi-hop reasoning over large knowledge corpora. The implementation is available at GitHub.

ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online emotional support. However, existing long-term dialogue benchmarks primarily focus on static and explicit fact retrieval, failing to evaluate agents in critical scenarios where user information is dispersed, implicit, and continuously evolving. To address this gap, we introduce ES-MemEval, a comprehensive benchmark that systematically evaluates five core memory capabilities: information extraction, temporal reasoning, conflict detection, abstention, and user modeling, in long-term emotional support settings, covering question answering, summarization, and dialogue generation tasks. To support the benchmark, we also propose EvoEmo, a multi-session dataset for personalized long-term emotional support that captures fragmented, implicit user disclosures and evolving user states. Extensive experiments on open-source long-context, commercial, and retrieval-augmented (RAG) LLMs show that explicit long-term memory is essential for reducing hallucinations and enabling effective personalization. At the same time, RAG improves factual consistency but struggles with temporal dynamics and evolving user states. These findings highlight both the potential and limitations of current paradigms and motivate more robust integration of memory and retrieval for long-term personalized dialogue systems.

Inferential Question Answering

Despite extensive research on a wide range of question answering (QA) systems, most existing work focuses on answer containment-i.e., assuming that answers can be directly extracted and/or generated from documents in the corpus. However, some questions require inference, i.e., deriving answers that are not explicitly stated but can be inferred from the available information. We introduce Inferential QA -- a new task that challenges models to infer answers from answer-supporting passages which provide only clues. To study this problem, we construct QUIT (QUestions requiring Inference from Texts) dataset, comprising 7,401 questions and 2.4M passages built from high-convergence human- and machine-authored hints, labeled across three relevance levels using LLM-based answerability and human verification. Through comprehensive evaluation of retrievers, rerankers, and LLM-based readers, we show that methods effective on traditional QA tasks struggle in inferential QA: retrievers underperform, rerankers offer limited gains, and fine-tuning provides inconsistent improvements. Even reasoning-oriented LLMs fail to outperform smaller general-purpose models. These findings reveal that current QA pipelines are not yet ready for inference-based reasoning. Inferential QA thus establishes a new class of QA tasks that move towards understanding and reasoning from indirect textual evidence.

Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language

Question-Answering (QA) models for low-resource languages like Bangla face challenges due to limited annotated data and linguistic complexity. A key issue is determining whether models rely more on pre-encoded (parametric) knowledge or contextual input during answer generation, as existing Bangla QA datasets lack the structure required for such analysis. We introduce BanglaCQA, the first Counterfactual QA dataset in Bangla, by extending a Bangla dataset while integrating counterfactual passages and answerability annotations. In addition, we propose fine-tuned pipelines for encoder-decoder language-specific and multilingual baseline models, and prompting-based pipelines for decoder-only LLMs to disentangle parametric and contextual knowledge in both factual and counterfactual scenarios. Furthermore, we apply LLM-based and human evaluation techniques that measure answer quality based on semantic similarity. We also present a detailed analysis of how models perform across different QA settings in low-resource languages, and show that Chain-of-Thought (CoT) prompting reveals a uniquely effective mechanism for extracting parametric knowledge in counterfactual scenarios, particularly in decoder-only LLMs. Our work not only introduces a novel framework for analyzing knowledge sources in Bangla QA but also uncovers critical findings that open up broader directions for counterfactual reasoning in low-resource language settings.

Structured Over Scale: Learning Spatial Reasoning from Educational Video

Vision-language models (VLMs) demonstrate impressive performance on standard video understanding benchmarks yet fail systematically on simple reasoning tasks that preschool children can solve, including counting, spatial reasoning, and compositional understanding. We hypothesize that the pedagogically-structured content of educational videos provides an ideal training signal for improving these capabilities. We introduce DoraVQA, a dataset of 5,344 question-answer pairs automatically extracted from 8 seasons of Dora the Explorer with precise timestamp alignment. Each episode follows a consistent \textit{context-question-pause-answer} structure that creates a self-contained learning environment analogous to interactive tutoring. We fine-tune both Qwen2 and Qwen3 using Group Relative Policy Optimization (GRPO), leveraging the clear correctness signals and structured reasoning traces inherent in educational content. Despite training exclusively on 38 hours of children's educational videos, our approach achieves improvements of 8-14 points on DoraVQA and state-of-the-art 86.16\% on CVBench, with strong transfer to Video-MME and NExT-QA, demonstrating effective generalization from narrow pedagogical content to broad multimodal understanding. Through cross-domain benchmarks, we show that VLMs can perform tasks that require robust reasoning learned from structured educational content, suggesting that content structure matters as much as content scale.

MiNER: A Two-Stage Pipeline for Metadata Extraction from Municipal Meeting Minutes

Municipal meeting minutes are official documents of local governance, exhibiting heterogeneous formats and writing styles. Effective information retrieval (IR) requires identifying metadata such as meeting number, date, location, participants, and start/end times, elements that are rarely standardized or easy to extract automatically. Existing named entity recognition (NER) models are ill-suited to this task, as they are not adapted to such domain-specific categories. In this paper, we propose a two-stage pipeline for metadata extraction from municipal minutes. First, a question answering (QA) model identifies the opening and closing text segments containing metadata. Transformer-based models (BERTimbau and XLM-RoBERTa with and without a CRF layer) are then applied for fine-grained entity extraction and enhanced through deslexicalization. To evaluate our proposed pipeline, we benchmark both open-weight (Phi) and closed-weight (Gemini) LLMs, assessing predictive performance, inference cost, and carbon footprint. Our results demonstrate strong in-domain performance, better than larger general-purpose LLMs. However, cross-municipality evaluation reveals reduced generalization reflecting the variability and linguistic complexity of municipal records. This work establishes the first benchmark for metadata extraction from municipal meeting minutes, providing a solid foundation for future research in this domain.

Leveraging LLMs For Turkish Skill Extraction

Skill extraction is a critical component of modern recruitment systems, enabling efficient job matching, personalized recommendations, and labor market analysis. Despite Türkiye's significant role in the global workforce, Turkish, a morphologically complex language, lacks both a skill taxonomy and a dedicated skill extraction dataset, resulting in underexplored research in skill extraction for Turkish. This article seeks the answers to three research questions: 1) How can skill extraction be effectively performed for this language, in light of its low resource nature? 2)~What is the most promising model? 3) What is the impact of different Large Language Models (LLMs) and prompting strategies on skill extraction (i.e., dynamic vs. static few-shot samples, varying context information, and encouraging causal reasoning)? The article introduces the first Turkish skill extraction dataset and performance evaluations of automated skill extraction using LLMs. The manually annotated dataset contains 4,819 labeled skill spans from 327 job postings across different occupation areas. The use of LLM outperforms supervised sequence labeling when used in an end-to-end pipeline, aligning extracted spans with standardized skills in the ESCO taxonomy more effectively. The best-performing configuration, utilizing Claude Sonnet 3.7 with dynamic few-shot prompting for skill identification, embedding-based retrieval, and LLM-based reranking for skill linking, achieves an end-to-end performance of 0.56, positioning Turkish alongside similar studies in other languages, which are few in the literature. Our findings suggest that LLMs can improve skill extraction performance in low-resource settings, and we hope that our work will accelerate similar research on skill extraction for underrepresented languages.

Error Taxonomy-Guided Prompt Optimization

Automatic Prompt Optimization (APO) is a powerful approach for extracting performance from large language models without modifying their weights. Many existing methods rely on trial-and-error, testing different prompts or in-context examples until a good configuration emerges, often consuming substantial compute. Recently, natural language feedback derived from execution logs has shown promise as a way to identify how prompts can be improved. However, most prior approaches operate in a bottom-up manner, iteratively adjusting the prompt based on feedback from individual problems, which can cause them to lose the global perspective. In this work, we propose Error Taxonomy-Guided Prompt Optimization (ETGPO), a prompt optimization algorithm that adopts a top-down approach. ETGPO focuses on the global failure landscape by collecting model errors, categorizing them into a taxonomy, and augmenting the prompt with guidance targeting the most frequent failure modes. Across multiple benchmarks spanning mathematics, question answering, and logical reasoning, ETGPO achieves accuracy that is comparable to or better than state-of-the-art methods, while requiring roughly one third of the optimization-phase token usage and evaluation budget.

MedViz: An Agent-based, Visual-guided Research Assistant for Navigating Biomedical Literature

Biomedical researchers face increasing challenges in navigating millions of publications in diverse domains. Traditional search engines typically return articles as ranked text lists, offering little support for global exploration or in-depth analysis. Although recent advances in generative AI and large language models have shown promise in tasks such as summarization, extraction, and question answering, their dialog-based implementations are poorly integrated with literature search workflows. To address this gap, we introduce MedViz, a visual analytics system that integrates multiple AI agents with interactive visualization to support the exploration of the large-scale biomedical literature. MedViz combines a semantic map of millions of articles with agent-driven functions for querying, summarizing, and hypothesis generation, allowing researchers to iteratively refine questions, identify trends, and uncover hidden connections. By bridging intelligent agents with interactive visualization, MedViz transforms biomedical literature search into a dynamic, exploratory process that accelerates knowledge discovery.

JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual Résumés and JDs

We introduce JobResQA, a multilingual Question Answering benchmark for evaluating Machine Reading Comprehension (MRC) capabilities of LLMs on HR-specific tasks involving résumés and job descriptions. The dataset comprises 581 QA pairs across 105 synthetic résumé-job description pairs in five languages (English, Spanish, Italian, German, and Chinese), with questions spanning three complexity levels from basic factual extraction to complex cross-document reasoning. We propose a data generation pipeline derived from real-world sources through de-identification and data synthesis to ensure both realism and privacy, while controlled demographic and professional attributes (implemented via placeholders) enable systematic bias and fairness studies. We also present a cost-effective, human-in-the-loop translation pipeline based on the TEaR methodology, incorporating MQM error annotations and selective post-editing to ensure an high-quality multi-way parallel benchmark. We provide a baseline evaluations across multiple open-weight LLM families using an LLM-as-judge approach revealing higher performances on English and Spanish but substantial degradation for other languages, highlighting critical gaps in multilingual MRC capabilities for HR applications. JobResQA provides a reproducible benchmark for advancing fair and reliable LLM-based HR systems. The benchmark is publicly available at: https://github.com/Avature/jobresqa-benchmark