Question Answering

Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult because partial evidence can make an unsupported answer appear plausible. We study selective answering through evidence sufficiency boundaries: for the same question, a model should abstain under unsupported or partially supported context, answer when the context first becomes sufficient, and keep the answer stable when redundant evidence is added. We introduce Evidence Sufficiency Boundary Training, a generation-native training framework that constructs ordered evidence chains and supervises the abstain-to-answer transition directly. The method combines level supervision, a boundary flip margin, post-boundary stability, and answer recall protection. We build evidence chains from HotpotQA, 2WikiMultiHopQA, and MuSiQue, then evaluate models with chain metrics, raw QA utility, and unsupported-answer rates on external non-answerable sets. With Qwen2.5-3B-Instruct and LoRA adaptation, Evidence Sufficiency Boundary Training gives the strongest boundary localization among the tested systems, with flip accuracy of 0.807 compared with 0.781 for a token-level abstention baseline. It also achieves the lowest overall unsupported-answer rate on external non-answerable evaluation, 0.095 compared with 0.101 for the same baseline, while retaining competitive raw QA F1. The results show that grounded selective answering improves when training marks the evidence level where refusal should give way to answering.

Dialectal Arabic (DA) remains under-resourced compared to Modern Standard Arabic (MSA), particularly for machine reading comprehension (MRC) and question answering (QA). Existing Arabic QA benchmarks primarily focus on formal written MSA or multiple-choice QA, with limited coverage of naturally spoken dialects. Here, we aim to bridge this gap. We introduce EDRAC, the first large-scale benchmark for dialectal Arabic machine reading comprehension (MRC) and generative QA, covering five major dialects: Egyptian, Moroccan, Emirati, Syrian, and Saudi Arabic. EDRAC contains 499 passages derived from naturally occurring spoken interactions and 4,977 corresponding QA pairs generated through a human--LLM collaborative pipeline combining iterative generation, LLM-as-a-judge evaluation, and human verification. We benchmark Arabic-centric and multilingual LLMs on EDRAC using lexical and semantic metrics. Our results reveal substantial gaps between semantic answer quality and dialectal fidelity, highlighting the limitations of existing evaluation metrics for dialectal Arabic generation. EDRAC provides a realistic and challenging MRC benchmark for future research on dialectal Arabic NLP.

Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high cost for unsupported or wrong automatic answers. We deploy a system that answers only from a closed set of verified QA units: it returns a retrieved unit verbatim, or routes to clarify, abstain, or handoff. The index is enriched offline by staged linguistic seeding (SLS): a human authors a per-unit world-grounded slot recipe, gpt-4.1-mini renders it into variants, and a light human gate filters them. One methodology is reused across both domains, so inference stays a single retrieval pass with no query-time generation. On held-out query variants from two industrial domains, SLS lifts hybrid R@1 to 0.881/0.930 (+0.27/+0.34), with gains across all five retrievers tested. At the same gpt-4.1-mini generation budget, SLS beats doc2query by +0.20/+0.32, while cross-provenance evaluation provides additional evidence of transfer across generated-query distributions. Verified-unit answering also removes free-form generation's unsupported-content surface (7-13% versus approximately 0%). We report this as an application study, including negative results.

Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of intermediate steps. It is hard to separate their contributions from the final result. In this paper, we propose a dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts. We first extract structured facts from raw observations and organize them into an explicit fact store. To support credit assignment, we then cluster semantically equivalent facts and infer the posterior utility of each fact cluster using Bayesian estimation over group rollouts. Finally, we convert the estimated fact utilities into dense step-level rewards to guide RL training. Experiments on seven single-hop and multi-hop QA benchmarks show that our method consistently outperforms existing baselines. Ablation studies validate clear relative improvements on multi-hop QA compared to outcome reward-only training.

Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data on every call. We study an alternative: compiling a knowledge graph offline into a bank of LoRA adapters, one per entity, that serve as a parametric knowledge layer queried by injecting weights rather than text, at zero query-time context cost. On the MetaQA dataset, we find that subgraph-trained adapters encode context-free factual knowledge that generalizes to unseen questions: on single-valued relations the adapter gains $+0.243$ exact-match score over a base model that is nearly blind closed-book ($0.007$), and only the correct adapter recovers this knowledge (an oracle gap of $+0.283$ over the base model). However, the stored knowledge is not recoverable by similarity: given a query with no subgraph, embedding-based and weight-space geometry retrieval both perform at chance, because a semantically neighbouring entity's adapter does not contain the answer - knowledge is stored locally and does not transfer. Weight geometry correlates with subgraph semantics ($ρ= +0.329$) but not with functional retrievability. We quantify the byte and context-token costs against graph retrieval-augmented generation and discuss deployment implications. Our results establish that parametric knowledge graph memory is feasible for storing knowledge, and identify selecting and composing the right adapters by a mechanism other than semantic similarity as the central open problem - motivating a learned, query-conditioned composition mechanism.

Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs represent uncertainty through a single predictive distribution, conflating epistemic ignorance with genuine ambiguity. We introduce Credal Large Language Models (CLLMs): an ensemble of LoRA adapters induces a credal set whose lower and upper probabilities expose the spread of plausible predictive distributions rather than collapsing to a single softmax output. From this representation, we derive a single commitment rule: the model commits to an answer only when its lower probability exceeds the upper probability of every alternative, and otherwise returns the set of answers that no plausible predictor rules out. We apply this commitment rule at two depths: Credal Token Commitment (CTC) applies it to answer tokens from one ensemble forward pass, which decides constrained answers without any generation; for open-ended answers, credal decoding extends a partial answer only when no completed answer dominates it, so that the completions produced are those the plausible predictors license, and Credal Semantic Commitment (CSC) applies the rule to their meaning clusters. We evaluate CLLMs with Gemma-2-9B, Llama-3.1-8B and Qwen2.5-7B on OpenBookQA, CoQA, TriviaQA and ARC-Challenge. On multiple choice, CTC commits on 73-91% of questions at 89-98% accuracy, returns sets of 1.1-1.5 options containing the gold one on 89-98%, and its intervals contain the observed accuracy in 24 of 30 confidence bins without calibration; corrupted context lowers commitment from 87-92% to 65-71%, and on Gemma the credal bound detects corruption better than every baseline. On open-ended QA, CLLM outperforms semantic entropy and Laplace-LoRA at a fixed coverage by up to 19% and 9.5% absolute accuracy on CoQA and TriviaQA with context, for every backbone.

Graph RAG connects facts no single passage states, but implementations pay three times: in infrastructure, keeping vector store, graph database and document store in sync; in quality, because a pipeline that never refuses extractor output stores edges that assert nothing; and over time, because a graph that only accumulates treats superseded and current facts alike. post-graph-rag is an open-source engine addressing all three. Chunks with embeddings, a canonical entity graph and community summaries live in one PostgreSQL database, with pgvector for search and edge tables for traversal. Extraction output is validated before writing: vague predicates, pronominal names and bare quantities are rejected, predicates normalise onto an optional vocabulary, entities resolve to one vertex per canonical name, and denials keep the positive predicate under a negation flag. A bi-temporal layer records when a relation held and when the system believed it, superseding incompatible earlier assertions from document order. Against LightRAG on three corpora with extraction and embedding models fixed, it builds a denser graph everywhere, up to $2.4\times$ the relations per entity, and a more queryable one: 0.46-0.58 distinct edge labels per relation against 0.77-1.33. It supersedes 13 and 8 relationships where the baseline, having no temporal model, supersedes none. On LongMemEval, 500 questions of long-horizon chat memory, it scores 85.8 percent with gemini-3.6-flash against 71.2 for Zep's gpt-4o and 60.2 for a full-context baseline, leading on all six question types. The largest single contribution is temporal grounding in the prompt: carrying each relation's validity period through to synthesis moves temporal reasoning from 0.496 to 0.881, ablated paired on one graph per instance. Code: post-graph-rag https://github.com/crajah/post-graph-rag; post-graph https://github.com/crajah/post-graph

Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question answering, verbalized model overconfidence may be associated with the consistency of the generated supporting rationales. In this paper, we study whether corresponding changes in the lexical diversity of generated answer rationales accompany changes in model confidence induced by instruction tuning. We evaluate three matched base and instruction-tuned models across question-answering benchmarks and find that instruction tuning consistently alters answer confidence, despite limited changes in predictive accuracy and decreases in likelihood-based calibration. Secondly, we observe a non-uniform effect of instruction tuning on rationale diversity: cross-rationale diversity consistently decreases, whereas surface-level lexical diversity varies in both direction and magnitude across models and benchmarks. Finally, we find that these differences persist after controlling for answer selection and rationale length, confirming that confidence and rationale diversity capture distinct effects of instruction tuning.

Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question answering. Recent approaches either translate retrieved documents into English or the query language to bridge the cross-lingual semantic gap, or decompose a complex query into sub-questions and aggregate the intermediate reasoning process. However, both lines of work suffer from two limitations. First, one-size-fits-all translation alignment, blanket translation discards culturally and linguistically native information unique to the target language, introduces translation noise, and inflates system cost. Second, greedy decomposition and aggregation, uncontrolled decomposition produces redundant sub-questions that compound errors during step-wise reasoning, and the final aggregation over reasoning paths further amplifies these errors. We address both with our method Syfer, a synthesizer-folding framework for multilingual multi-hop question answering that defers translation rather than applying it by default. Syfer first invokes a format-constrained decomposer to produce a sub-question graph in the original language, followed by a decomposition-quality check; when the check passes, sub-questions are answered sequentially under a retrieve-then-answer policy in the target language, and the English translation pathway with bilingual sub-question graph alignment is activated only when the check fails. Experiments across multiple languages show that Syfer attains competitive accuracy while striking a favourable balance between performance and computational cost.

Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms correctly. We study compound options connected by AND, OR, and NEITHER/NOR, introducing a framework that decomposes each option into atomic answers and scores contrastive hypotheses about each one, so the model never sees a compound option. An operator-constrained integer linear program then composes the calibrated scores into a single prediction. We evaluate on LOGICAL-COMMONSENSEQA and introduce LOGICAL-SATA, a reading-comprehension benchmark derived from SATA-Bench. Our framework improves Macro-F1 from 48.3 to 77.0 on the human-validated LOGICAL-COMMONSENSEQA split and from 47.0 to 75.6 on LOGICAL-SATA, with the largest gains on NEITHER/NOR.

Large language models (LLMs) may generate fluent but incorrect answers, making uncertainty quantification important for reliable question answering. However, heuristic uncertainty scores cannot perfectly distinguish correct predictions from incorrect ones, and directly applying a fixed uncertainty threshold provides no statistical control over the error rate among accepted answers. To address this limitation, we propose A-CRC-QA, a post-hoc calibration framework for uncertainty-aware selective question answering. The proposed method reformulates selection-conditioned error control as a linear expectation constraint and applies a monotonized empirical-risk calibration procedure inspired by conformal risk control. Since the resulting instance-wise loss is generally non-monotone with respect to the acceptance threshold, our framework targets asymptotic rather than finite-sample risk control. A-CRC-QA is model-agnostic, requires no additional training, and can be combined with different uncertainty estimators. Experiments on CoQA and MedMCQA demonstrate its applicability to both open-ended and closed-ended question answering, achieving a favorable trade-off between accepted-answer reliability and answer retention compared with uncalibrated and confidence-bound-based baselines.

Reliability estimation of large language models is in many cases as crucial as their accuracy, as reliable models are more trustworthy, robust, and suitable for practical applications. Recent advancements in natural language processing (NLP), particularly those based on transformer architectures, have significantly accelerated progress across various NLP tasks. This study focuses on the reliability of transformer-based question answering (QA) models, specifically BERT models and its variants (RoBERTa, ALBERT, DistilBERT). These encoder-only pretrained transformers have demonstrated remarkable accuracy in QA tasks that can be treated as classification tasks. However, their reliability remains underexplored. This study evaluates the reliability of four BERT-based models by assessing response stability under two conditions: (1) internal model variations induced via Monte Carlo Dropout (MCD) and (2) input perturbations through paraphrasing. Using the SQuAD and QuAC datasets, we investigate how dropout rates affect prediction consistency and whether lexical changes impact answer stability. Our findings reveal that RoBERTa maintains higher reliability, whereas AlBERT and DistilBERT exhibit significant inconsistencies. Statistical analyses confirm that enabling MCD during prediction does not disrupt inference dynamics, validating its effectiveness as a reliability metric. These findings underscore the importance of evaluating both accuracy and stability in QA models to ensure stability in real-world applications.

Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models to abstain when uncertain improves reliability but introduces a coverage accuracy tradeoff. We propose a two-stage framework for medical hypothesis verification in multiple-choice settings that manages this tradeoff through targeted ontology grounding, applied only when the model abstains. We show that abstention is not random but reflects genuine uncertainty, with abstained predictions associated with lower confidence. Across two frontier models (GPT-5.5, accessed via the Azure OpenAI API, and DeepSeek-R1), the proposed framework improves question-level accuracy by 9.6 percentage points (82.9% to 92.5%) and hypothesis-level accuracy by 4.2 percentage points (92.0% to 96.2%). Our experiments conducted on MedReason and MedQA show that abstention can be repurposed as a control signal for selective reasoning refinement, achieving knowledge-graph-level performance without explicit knowledge graph construction.

Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly in domain-specific contexts where general-purpose LLMs and RAG tend to underperform. We hypothesize that augmenting RAG with unstructured and structured knowledge, extracted from both documents and knowledge graphs (KGs), can improve reasoning and answer accuracy for such tasks. To test this, we propose KGCaRe, a hybrid approach that combines neural retrieval with symbolic reasoning over LLM-generated KGs. KGCaRe constructs a KG from documents using a multi-prompt extraction strategy and stores it in a graph database. Simultaneously, the documents are embedded into a vector store to enable neural retrieval. KGCaRe performs innovative iterative graph traversal guided by the LLM to extract relevant triples, prune irrelevant information, and uses additional clue entities to traverse the graph again if the initial traversal does not provide satisfactory context to generate the answer. The relevant triples extracted from the KG in path form, along with semantically retrieved text passages, are then fed into custom KGCaRe prompts to generate answers to the complex conditional questions with explanations. We evaluate KGCaRe on two complex conditional QA datasets. Our results on these datasets show that KGCaRe consistently outperforms existing baselines, including Vanilla LLM, Code Prompt, Text Prompt, Think-on-Graph, Vanilla RAG, and HybridContextQA, across multiple LLMs such as Mistral, Mixtral, GPT-3.5, and GPT-4o. We publicly release the software pipeline that we developed to implement the proposed KGCaRe approach.

Retrieval-Augmented Generation (RAG) is widely regarded as a novel paradigm born from the limitations of large language models (LLMs)--a mechanism to ground their outputs in external knowledge. This view, however, is incomplete when considered within a broader historical context. In this paper, we argue that the core ideas underlying RAG are not new: foundational concepts such as integrating retrieval and language generation, knowledge augmentation, answer verification, and iterative query (or prompt) refinement had already been studied and instantiated in information retrieval (IR) and question answering (QA) research dating back to the early 2000s, well before the emergence of LLMs. We make this case by systematically tracing the intellectual lineage of modern RAG and Agentic RAG back to their classical IR and QA antecedents, and examining why this continuity has gone under-recognized -- a consequence of community fragmentation, shifting terminology, and the recency bias endemic to fast-moving fields. Rather than treating LLMs as the origin point of retrieval-augmented intelligence, we propose viewing them as a new interface layer atop a decades-old QA architecture. This reframing is not merely historical: by situating RAG within the longer trajectory of IR research, we surface underutilized prior work -- on user modeling, answer validation, and query refinement -- that can directly inform next-generation RAG design, reducing unintentional rediscovery and fostering genuine cross-community integration.

False-presupposition QA (FPQA) tests LLMs on their ability to identify false presuppositions in questions and abstain or correct them rather than reinforcing false assumptions. The common approach reduces the task to prompting LLMs to extract presuppositions and fact checking each presupposition. While the performance on dedicated benchmarks keeps improving, evaluation largely focuses on questions with false presuppositions (FPQs) while ignoring the performance on ``normal'' questions (TPQs). Since many benchmarks over-represent FPQs compared to their natural occurrence, the result is that performance on these benchmarks doesn't reflect real-world QA performance. Through extensive experiments across various model families, sizes, and benchmarks, we show that methods that perform better on FPQs tend to perform worse on TPQs. Our analysis reveals this is the result of weak fact checking modules that reject also true presuppositions. We hope our findings will help guide future work toward FPQA methods that generalize well to realistic settings.

Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often leading to incomplete or incorrect output. We propose NeSy-RAG, a modular neuro-symbolic RAG framework that synthesizes attributable Prolog modules from retrieved text chunks. For each chunk, the system generates semantically meaningful predicates that encode Boolean claims, which may depend on user facts. Using joint natural language-code embeddings, predicates are retrieved and composed into Prolog queries. To address incomplete user context, we introduce a symbolic knowledge-gap detection mechanism that identifies missing user facts whose truth values affect the query outcome and automatically triggers follow-up interactions. Executing the resulting Prolog queries yields deterministic answers together with transparent execution traces that link each reasoning step to its originating source. On the ShARC benchmark, without domain-specific training, NeSy-RAG achieves 61.1% accuracy, outperforming a same-model RAG baseline that achieves 42.8% accuracy.

Large language models (LLMs) are increasingly used for question answering, education, and research, including in religious and cultural domains where answers depend on specialised source traditions. Yet in Islamic Studies, key concepts, methods, and debates preserved in the authoritative scholarly tradition, known as turath, lack high-quality annotated resources. We introduce IslamicTurathBench (ISTB), a multi-task, multi-discipline dataset for evaluating LLMs on classical Islamic scholarship. Developed and reviewed by domain experts, ISTB contains 3,465 question-answer items drawn from 35 recognised source works spanning more than 12 centuries of scholarship across seven key fields of Islamic Studies. To enable comprehensive profiling of model capabilities, ISTB is structured along two axes: scholarly demand (Beginner, Intermediate, and Advanced) and task format (multiple-choice questions, passage-based comprehension, and open-ended knowledge questions). ISTB includes aggregated scores from a scholarly human reference panel and zero-shot baselines from ten systems. The dataset supports reproducible evaluation of language-model behaviour across source works, disciplines, scholarly-demand levels, and question formats in a historically layered scholarly domain.

Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge. Retrieval-augmented generation (RAG) addresses this limitation by integrating external knowledge and excelling at single-hop queries. However, it struggles with multi-hop questions that require cross-document reasoning. Existing methods, such as graph structured RAG or question decomposition, often lack dynamic decomposition and effective filtering, which leads to lower efficiency and accuracy. To overcome these limitations, we propose Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation (D2F-ReAG), a novel paradigm that adaptively controls reasoning depth by judging the reliability of the root-level reasoning. If the root reasoning is reliable, the model directly generates the answer. Otherwise, the question is logically decomposed into sub-questions, and the verified reasoning derived from these sub-questions is used to refine the root reasoning. Experiments on three multi-hop benchmarks demonstrate the effectiveness of our method in handling complex multi-hop questions.

Large language models can generate fluent responses to Islamic questions while introducing factual errors that are difficult to identify. This paper presents our system for \textsc{HalluScoring 2026} Task 2.1, \textit{Islamic Hallucination Detection and Find the Truth}. The task requires a unified two-step prediction: determining whether an Arabic answer generated by an LLM is hallucinated and selecting the verified answer from six closely related candidate options. We use the Islamic knowledge dataset provided by the shared task, which contains 600 question--answer instances, including 341 hallucinated and 259 non-hallucinated answers. Our system is based on the fine-tuned \texttt{google/gemma-4-12B-it} model and uses deterministic decoding during inference. The generated outputs are normalized to extract the hallucination label and the selected option. The system achieves a Macro-F1 score of 0.928 and a label accuracy of 0.935 for hallucination detection, together with an option accuracy of 0.895 for answer selection. These results yield a combined score of 0.912, demonstrating strong performance across both stages of the task. The lower option-selection accuracy indicates that distinguishing the verified answer from plausible alternatives remains more challenging than detecting hallucinated responses.

Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in high-stakes domains such as human and veterinary medicine. However, this does not guarantee that generated claims are faithful to the provided excerpts. We present VetScore, a multi-step evaluation method for veterinary long-form question answering, designed to assess how well are generated claims supported by the provided excerpts, weighing this information by each claim's harm potential. VetScore first segments the output and decomposes it into individual claims, then scores each claim with respect to its harm potential and evaluates its faithfulness to source excerpts, and finally calculates the overall risk-adjusted score. We collect an expert-annotated meta-evaluation dataset, evaluate our approach with a range of judge models, and show that it achieves high correlations with veterinary experts even with small judge models, while offering explainability across multiple dimensions.

How can question answering (QA) systems determine whether a query is ambiguous? Ambiguity detection is essential in open-domain QA, as misclassification leads to answering the wrong interpretation or unnecessary clarification. However, existing methods conflate answer diversity with ambiguity, leading to inaccurate predictions. They also process queries uniformly, resulting in wasteful computation. We propose ARCHIVE (Ambiguity Recognition via Cascaded Hypothesis Inspection and Conflict Verification), an accurate and efficient framework that detects ambiguity via logical conflict: a query is ambiguous when its valid answers cannot all be true under a single interpretation. ARCHIVE combines a lightweight early-exit encoder for surface-detectable cases with a conflict reasoning module that models logical relations among answers, reinforced by an invariance objective for robustness to noisy answer sets. We present QuireQA, a 4,703-query benchmark spanning factoid, non-factoid, and ill-formed queries. Experiments show ARCHIVE outperforms competitors, improving F1-amb by up to 10.4% and F1-unamb by up to 21.6%, while operating 16$\times$ faster than the best competitor.

Code agents spend much of their effort simply locating the right code inside a repository. Two approaches dominate current practice. In Semantic Search, the agent retrieves code blocks from a vector index built from the repository in advance. In Deep Agentic Search (also known as grep-search by subagent), a planning agent delegates the exploration to a separate subagent that works in an isolated context window and returns only a condensed result. The second design, which is considered good context engineering practice, exists to protect the main agent from context pollution (also known as context rot), the loss of accuracy that occurs as unrelated material accumulates in the context window. Recent code agents (such as Claude Code, Codex, Antigravity, etc) have adopted it quickly, but there is little evidence on whether it produces better answers. We compare the two approaches on SWE-QA, a benchmark for repository-level code question answering. Semantic search answered 65.2% of questions correctly against 46.2% for deep agentic search, and it produced each correct answer at less than half the cost. To explain the gap, we then coded every failed run into a taxonomy of failure modes. The taxonomy shows that deep agentic search did not remove failures but introduced a new class of them: the single largest share of its failures, 41.8%, occurred at the hand-off between the planner and its sub-agent, and these were usually silent, ending in a fluent and confident answer that was wrong. Deep agentic search addresses a real problem and is now the preferred design in many code agents. However, our results show that the protection it offers may not be free, and that for read-only questions over a repository that can be indexed, retrieval was the stronger and cheaper option.

Verification for retrieval-augmented generation usually scores each retrieved chunk and drops the ones that fail. We show this cannot work for multi-hop questions, and show what does. Per-chunk scoring assumes one chunk is a sufficient premise for the answer. Multi-hop questions are built so that none is, and the paragraph carrying the answer is the one the question does not name. Entailment scoring reaches 0.643, 0.523 and 0.560 AUC on HotpotQA, 2WikiMultihopQA and MuSiQue, against 0.951 on single-hop SQuAD. Seven controls rule out model capacity, premise length, hypothesis template, decision threshold, retriever, answer-matching criterion and prompt. End to end across three datasets, three generator sizes and two prompts, per-chunk gating is significantly worse than not filtering at all in every cell, and its penalty grows with generator capability. The repair is to condition verification on the decomposed sub-question rather than the original query. Using MuSiQue's gold decomposition, entailment on a later hop rises from 0.546, which is chance, to 0.840, a paired lift of +0.355 with a bootstrap interval of [0.331, 0.382]. An off-the-shelf Qwen2.5-7B decomposer, given the question and the top retrieved paragraph, reaches 0.637 and captures 31% of that ceiling; decomposing without retrieval reaches 0.533, below the original question. Iterative retrieval systems already produce such decompositions and discard them before verifying.

Generative Artificial Intelligence (AI) is increasingly used by Muslims for religious guidance, Qur'anic interpretation, Hadith explanation, jurisprudential rulings, and Islamic education. Despite its growing adoption, there is limited empirical evidence on whether current AI systems provide authentic, verifiable, and trustworthy Islamic knowledge suitable for high-trust religious contexts. This study evaluates six leading generative AI systems using fifty realistic open-ended Islamic questions covering Qur'anic interpretation, Hadith, Fiqh, ethics, pastoral advice, and Madhhab-sensitive topics. Responses were collected under real-world conditions from participants in Australia and the United Kingdom and analysed using a mixed-method framework examining domain accuracy, citation verification, hallucinations, jurisprudential consistency, uncertainty handling, source provenance, and geographical variation. The study addresses four research questions: (1) How accurate and authentic are AI-generated responses across major Islamic knowledge domains? (2) To what extent do AI systems produce hallucinations, incomplete citations, or unverifiable religious references? (3) How consistently do models handle jurisprudential disagreement, Madhhab diversity, and uncertainty? (4) Are current AI systems sufficiently reliable for religious guidance, Islamic education, and scholarly research? Overall, current generative AI systems are valuable as assistive tools for introductory Islamic learning but should not be treated as authoritative sources for religious rulings or Islamic research without verification against authenticated primary sources and qualified scholarly expertise. This study provides one of the first comprehensive empirical evaluations of AI reliability within Islamic knowledge, offering practical guidance for researchers, educators, AI developers, and the wider Muslim community.

Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook answerable Shifted IC cases and cover limited OOC shifts. To fill this gap, we present MMOOC, a large-scale benchmark for evaluating refusal and robust answering abilities of MLLMs. MMOOC contains over 41K image-question pairs, including answerable Shifted IC cases and unanswerable OOC cases, spanning three question formats, eight shift types and six visual scenarios, with data quality ensured through MLLM-based filtering and human verification. We evaluate model responses using Accuracy and Refusal Rate, and further introduce an LLM-as-a-Judge metric to assess the correctness of model reasoning. Experiments on diverse MLLMs show that current models still struggle to balance answer-ability and refusal under shifted contexts. We further analyze key failure patterns and show that post-training can improve robustness. MMOOC will be made publicly available.

Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting SQL tables. In this work we show that the operations that such knowledge bases allow can be replicated with zero ingestion costs (not even a vector database); in fact our solution, Zero-Ingestion ScalableRAG, handily out-performs all baselines (including knowledge graph approaches) in three out of the six corpora considered here, and only marginally missing maximum performance on the other three, with average accuracy across all six datasets 7.36% above the next most competitive baseline. It achieves this by keeping a workspace of document sets and values sets that it can write into and read from, allowing for on-the-fly aggregative reasoning in all situations where grouping is required on a primary key that is in one to one correspondence with a subset of the total document set. Capping the number of LLM calls by a constant independent of the corpus size, we also introduce Limited-Ingestion ScalableRAG, which does use a minimal vector database as well as an automated pattern discovery from a sample of documents, to further improve accuracy at scale. Our code is available at https://github.com/cohesity/ScalableRAG .

Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source documents. However, existing systems often attach citations that are topically related but insufficient to support their claims. We identify attribution ambiguity as a structural challenge: end-to-end generation must implicitly resolve combinatorial claim--document assignments, obscuring evidential boundaries and increasing the risk of evidence-boundary overrun, where claims exceed cited support. To address this challenge, we propose CAGE (Cognitive Attribution Graphs for Citation Generation), a two-stage framework that introduces an explicit cognitive attribution map before answer generation. CAGE first trains a plug-and-play Cognitive Map Induction Model to construct answer-centered support subgraphs, aligning each semantic answer unit with supporting documents through explicit relations. A Structured Citation Reasoning Model then realizes these units as sentence-level claims with map-aligned citations. Experiments on ASQA, ELI5, and ExpertQA show that CAGE achieves state-of-the-art performance, demonstrating the effectiveness of attribution-space contraction and map-guided citation generation.

We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA, so a system can answer questions about a corpus closed-book: no retrieval and no context-window budget. Across roughly 100 training runs from single documents to a 99-document corpus, we find that once adapter capacity is adequate, training-data quality is the dominant lever on closed-book accuracy, outweighing LoRA rank, learning rate, and two alternative architectures combined; capacity itself is a hard gate below which no data intervention helps. A single curation pass (shortening gold answers to canonical 1-6 word spans and dropping trivia) moved closed-book accuracy from 57.7% to 85.7% on a 15-document corpus, a larger jump than any architectural change. We confirm a capacity trend (rank must grow with corpus size) entangled with a coupling between rank and learning rate that we initially misdiagnosed. On a 15-document slice we add a real retrieval baseline: the internalized adapter (84.2% recall) beats a BM25-RAG pipeline with a base reader (58.9%) and even a realistic gold-chunk oracle (65.6%) at lower latency. We report the full arc, including three misdiagnoses, as a case study in debugging LLM training empirically.

Quiz rooms, trivia nights, and quiz shows challenge human knowledge across a wide range of topics, from canonical facts to everyday culture. In this paper, we examine whether large language models (LLMs) can perform competitively in such settings, using quiz-style questions to test them on both common and niche topics. We introduce TriviaRoomQA, a multilingual benchmark designed to evaluate everyday, culturally grounded, and long-tail knowledge across 288 topics. The benchmark contains 3,300 parallel multiple-choice questions in six European languages and additional 5,340 French-only questions for a more fine-grained case study. We evaluate 30 open-weight LLMs from European, Asian, and North American providers, covering models from 7 to 70B parameters. We find that models are strong on knowledge-intensive topics such as history, geography, and mathematics, but substantially weaker on everyday popular-culture topics such as celebrities, music, movies, and news. Moreover, model performance varies across languages even for the same underlying questions, suggesting that access to factual knowledge is not always language-independent. In sum, our dataset and experiments demonstrate an important knowledge gap which is not captured by existing academic-based saturated benchmarks.