Retrieval Granularity as Evidence Design in Small-Model RAG Question Answering: A Diagnostic HotpotQA Study

AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering

Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted. With a growing share of question answering systems built on top of commercial language model APIs, a method that can decide how much to retrieve, and how far to trust its own answers, without retraining the underlying model, is of clear practical value. This paper presents AB-RAG (Adaptive Budgeted Retrieval-Augmented Generation), a training-free and backbone-agnostic framework that generates an answer, estimates its confidence from a combination of three signals, and then decides whether to stop or to retrieve more evidence, subject to a fixed retrieval budget. The estimator combines the model's own certainty, the agreement between the answer and the evidence, and the variance of the retrieval scores. For models that expose token probabilities the certainty signal is read directly; for closed APIs it is approximated by self-consistency, so the method works without access to model internals. Across three backbones and two datasets, the central result is that the confidence estimate reliably separates correct from incorrect answers on every backbone, reaching a clean split of 57.6% against 0% Exact Match between high- and low-confidence answers on a factoid dataset. The adaptive policy improves accuracy on capable backbones, and the study reports its negative and nuanced findings honestly, including a confidence signal that proved unsuitable for short answers and a retrieval signal whose sign was found and corrected through measurement. The entire study was carried out on a single consumer laptop with only a few dollars of API spend.

Evaluating RAG approaches for Question Answering

LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering

Scientific literature is increasingly used as a knowledge source for language models, retrieval-augmented generation systems, and research assistants, but answering research questions from papers requires more than fluent generation. A reliable system must identify the relevant papers, locate the concrete evidence that supports the answer, and produce a response that is faithful to that evidence. We present LitTraceQA, a benchmark for literature-grounded question answering over scientific papers. Given a research question and a metadata pool of papers, a system must return three connected outputs: canonical paper identifiers, supporting evidence locations, and answers in one or more requested formats, including free-form text, multiple-choice answers, and structured tables. LitTraceQA targets evidence types common in scientific reading: tables, figures, text spans, equations or algorithms, and citation contexts. The public development split contains 55 examples, including 26 hidden-source single-paper questions and 29 multi-paper questions, and provides gold papers, evidence annotations, and answers for local validation. We also analyze a larger final annotation collection with 4,978 unique-question records over 4,859 unique gold papers. By evaluating paper retrieval, evidence grounding, and answer accuracy separately, LitTraceQA provides a testbed for scientific QA systems that produce verifiable answers rather than unsupported summaries.

Rank-ICL: Ranking-based In-context Learning for Search Result Explanation

Explanations in search results typically consist of text snippets or short passages presented alongside retrieved documents to help users efficiently assess relevance. While large language models (LLMs) have demonstrated strong performance across a wide range of language understanding and generation tasks, prior work on their use to generate explanations in search results remains relatively sparse. In this study, we investigate the use of decoder-only LLMs to generate explanations in the search results. To improve explanation quality in low-supervision settings, we introduce a ranking-based strategy for selecting informative few-shot examples in in-context learning. Rather than relying on randomly chosen demonstrations, relevant examples are dynamically retrieved based on retrieval functions to the input query–document pair. Evaluation on WikiSA and ExaRank shows that ranking-based few-shot prompting generally improves over zero-shot prompting and achieves competitive performance against random-shot prompting. However, its effectiveness varies across datasets, indicating that retrieval-based demonstration selection is beneficial but not uniformly superior in all settings.

Design and Implementation of a Retrieval-Augmented Generation (RAG) Based Chatbot for Document Question Answering

: With the rapid growth of enterprise databases, personal cloud storage, and corporate digital archives, the number of unstructured text documents requiring manual analysis and reading has increased massively. Extracting relevant information from massive multi-page documents manually is extremely time-consuming and prone to human oversight. Traditional keyword-based search systems and earlier rule-based chatbots do not really work that well anymore because they lack deep semantic understanding and fail to synthesize context-aware answers to user queries. This paper mainly talks about how Retrieval-Augmented Generation (RAG) frameworks are making document-based question-answering smarter and more reliable than traditional models. It explores different types of RAG techniques like dense retrieval, vector database optimization, generative language model integration, and hybrid search frameworks... and explains how they are implemented in real-world intelligent systems. The paper also discusses what these methods are good at, where they struggle a bit, and how practical they actually are when it comes to handling complex, multi-modal documents. One important thing the study shows is that RAG-based document chatbots can achieve contextual response accuracy levels of more than 95% and can reduce language model hallucinations quite a lot. Still, some problems are not fully solved yet — especially things related to processing nested tables within documents, sub-optimal retrieval latency, and parsing highly technical schemas in real time. Because of this, future research is expected to focus more on Graph-based RAG (GraphRAG), agentic multi-step reasoning, and privacy-preserving federated retrieval systems that can scale up dynamically as large document corpora evolve.

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K. In contrast, an MS MARCO-trained cross-encoder reranker reduces precision on the scientific corpus, suggesting that domain mismatch can outweigh the benefits of stronger query-passage interaction. Generation faithfulness measured with RAGAS increases with corpus scale in our setup. Retrieval evaluation uses pseudo-relevance labels derived from the hybrid system, so we treat the results as controlled comparative evidence rather than a benchmark claim. We release code, indexes, and evaluation outputs to support replication and follow-up studies.