While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge. Indeed, truthfulness requires more than accuracy – models must also recognize uncertainty and abstain when unsure to avoid hallucinations. This presents a fundamental challenge for existing methods: approaches that optimize for accuracy often amplify hallucinations, while those that encourage abstention can become overly conservative, sacrificing correct answers. Both extremes ultimately compromise truthfulness. In this work, we present TruthRL, a general reinforcement learning (RL) framework that directly optimizes the truthfulness of LLMs. Specifically, we implement TruthRL using GRPO with a simple yet effective ternary reward that distinguishes correct answers, hallucinations, and abstentions. It incentivizes models to reduce hallucinations not only by providing correct responses, but also by enabling abstention when uncertain, thereby improving truthfulness. Extensive experiments across four knowledge-intensive benchmarks show that TruthRL significantly reduces hallucinations (e.g., 43.5

Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging. Existing methods either lack generalization or are resource-intensive due to per-page LLM inference. In this paper, we introduce SCRIBES (**SCRI**pt-**B**ased Semi-Structured Content **E**xtraction at Web-**S**cale), a novel reinforcement learning framework that leverages layout similarity across webpages within the same site as a reward signal. Instead of processing each page individually, SCRIBES generates reusable extraction scripts that can be applied to groups of structurally similar webpages. Our approach further improves by iteratively training on synthetic annotations from in-the-wild CommonCrawl data. Experiments show that our approach outperforms strong baselines by over 13\% in script quality and boosts downstream question answering accuracy by more than 4\% for GPT-4o, enabling scalable and resource-efficient web information extraction.

Accurate recall from large-scale memories remains a core challenge for memory-augmented AI assistants performing question answering (QA), especially in similarity-dense scenarios where existing methods mainly rely on semantic distance to the query for retrieval. Inspired by how humans link information associatively, we propose AssoMem, a novel framework constructing an associative memory graph that anchors dialogue utterances to automatically extracted clues. This structure provides a rich organizational view of the conversational context and facilitates importance-aware ranking. Further, AssoMem integrates multi-dimensional retrieval signals—relevance, importance, and temporal alignment—using an adaptive mutual information (MI)-driven fusion strategy. Extensive experiments across three benchmarks and a newly introduced dataset, MeetingQA, demonstrate that AssoMem consistently outperforms state-of-the-art baselines, verifying its superiority in context-aware memory recall.

Wearable devices such as AI glasses are transforming voice assistants into always-available, hands-free collaborators that integrate seamlessly with daily life, but they also introduce challenges like egocentric audio affected by motion and noise, rapid micro-interactions, and the need to distinguish device-directed speech from background conversations. Existing benchmarks largely overlook these complexities, focusing instead on clean or generic conversational audio. To bridge this gap, we present WearVox, the first benchmark designed to rigorously evaluate voice assistants in realistic wearable scenarios. WearVox comprises 3,842 multi-channel, egocentric audio recordings collected via AI glasses across five diverse tasks including Search-Grounded QA, Closed-Book QA, Side-Talk Rejection, Tool Calling, and Speech Translation, spanning a wide range of indoor and outdoor environments and acoustic conditions. Each recording is accompanied by rich metadata, enabling nuanced analysis of model performance under real-world constraints. We benchmark leading proprietary and open-source speech Large Language Models (SLLMs) and find that most real-time SLLMs achieve accuracies on WearVox ranging from 29\% to 59\%, with substantial performance degradation on noisy outdoor audio, underscoring the difficulty and realism of the benchmark. Additionally, we conduct a case study with two new SLLMs that perform inference with single-channel and multi-channel audio, demonstrating that multi-channel audio inputs significantly enhance model robustness to environmental noise and improve discrimination between device-directed and background speech. Our results highlight the critical importance of spatial audio cues for context-aware voice assistants and establish WearVox as a comprehensive testbed for advancing wearable voice AI research.

End-to-end speech-in, speech-out dialogue systems are emerging as a powerful alternative to traditional ASR–LLM–TTS pipelines but remain prone to hallucinations due to limited factual grounding. While text-based dialogue models have effectively mitigated this issue through tools such as web search APIs, extending such capabilities to speech-in, speech-out systems remains underexplored. A key challenge is that tool integration increases latency, disrupting conversational flow. To mitigate this, we propose Streaming Retrieval-Augmented Generation (Stream RAG), a novel framework that reduces latency by predicting tool queries in parallel with user speech, even before the user finishes speaking. Specifically, we develop a post-training pipeline that teaches the model when to issue tool calls and how to generate spoken summaries using retrieved text results, thereby improving both accuracy and responsiveness. To evaluate our approach, we construct AudioCRAG, a benchmark created by converting queries from the publicly available CRAG dataset into speech form. Experimental results show that Stream RAG improves QA accuracy by over 20.0% absolute on AudioCRAG and achieves state-of-the-art performance, including outperforming cascaded systems, on the SLUE-SQA benchmark, while reducing latency by up to 57%. Stream RAG is modality-agnostic and can be applied equally to typed input, paving the way for more agentic, real-time AI assistants.

The advent of Large Language Models (LLMs) has significantly advanced web-based Question Answering (QA) systems over semi-structured content, raising questions about the continued utility of knowledge extraction for question answering. This paper investigates the value of triple extraction in this new paradigm by extending an existing benchmark with knowledge extraction annotations and evaluating commercial and open-source LLMs of varying sizes. Our results show that web-scale knowledge extraction remains a challenging task for LLMs. Despite achieving high QA accuracy, LLMs can still benefit from knowledge extraction, through augmentation with extracted triples and multi-task learning. These findings provide insights into the evolving role of knowledge triple extraction in web-based QA and highlight strategies for maximizing LLM effectiveness across different model sizes and resource settings.

Visual Question Answering (VQA) often requires coupling fine-grained perception with factual knowledge beyond the input image. Prior multimodal Retrieval-Augmented Generation (MM-RAG) systems improve factual grounding but lack an internal policy for when and how to retrieve. We propose PixSearch, the first end-to-end Segmenting Large Multimodal Model (LMM) that unifies region-level perception and retrieval-augmented reasoning. During encoding, PixSearch emits tokens to trigger retrieval, selects query modalities (text, image, or region), and generates pixel-level masks that directly serve as visual queries, eliminating the reliance on modular pipelines (detectors, segmenters, captioners, etc.). A two-stage supervised fine-tuning regimen with search-interleaved supervision teaches retrieval timing and query selection while preserving segmentation ability. On egocentric and entity-centric VQA benchmarks, PixSearch substantially improves factual consistency and generalization, yielding a 19.7

Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions. Our method is being deployed in production.

Existing recommendation systems either rely on user interaction logs, such as online shopping history for shopping recommendations, or focus on text signals. However, item-based histories are not always accessible and generalizable for multimodal recommendation. We hypothesize that a user's visual history --- comprising images from daily life --- can offer rich, task-agnostic insights into their interests and preferences, and thus be leveraged for effective personalization. To this end, we propose VisualLens, a novel framework that leverages multimodal large language models (MLLMs) to enable personalization using task-agnostic visual history. VisualLens extracts, filters, and refines a spectrum user profile from the visual history to support personalized recommendation. We created two new benchmarks, Google-Review-V and Yelp-V, with task-agnostic visual histories, and show that VisualLens improves over state-of-the-art item-based multimodal recommendations by 5-10\% on Hit@3, and outperforms GPT-4o by 2-5\%. Further analysis shows that VisualLens is robust across varying history lengths and excels at adapting to both longer histories and unseen content categories.

Can Large Language Models (LLMs) be trained to avoid hallucinating factual statements, and can Retrieval-Augmented Generation (RAG) be triggered only when necessary to reduce retrieval and computation costs? In this work, we address both challenges simultaneously. We introduce ConfQA, a fine-tuning strategy that reduces hallucination rates from 20-40

We introduce WearVQA, the first benchmark specifically designed to evaluate the Visual Question Answering (VQA) capabilities of multi-model AI assistant on wearable devices like smart glasses. Unlike prior benchmarks that focus on high-quality, third-person imagery, WearVQA reflects the unique challenges of ego-centric interaction-where visual inputs may be occluded, poorly lit, unzoomed, or blurry, and questions are grounded in realistic wearable use cases. The benchmark comprises 2,520 carefully curated image-question-answer triplets, spanning 7 diverse image domains including both text-centric and general scenes, 10 cognitive task types ranging from basic recognition to various forms of reasoning, and 6 common wearables-specific image quality issues. All questions are designed to be answerable using only the visual input and common senses. WearVQA is paired with a rigorous LLM-as-a-judge evaluation framework with 96

We introduce Memory-QA, a novel real-world task that involves answering recall questions about visual content from previously stored multimodal memories. This task poses unique challenges, including the creation of task-oriented memories, the effective utilization of temporal and location information within memories, and the ability to draw upon multiple memories to answer a recall question. To address these challenges, we propose a comprehensive pipeline, Pensieve, integrating memory-specific augmentation, time- and location-aware multi-signal retrieval, and multi-memory QA fine-tuning. We created a multimodal benchmark to illustrate various real challenges in this task, and show the superior performance of Pensieve over state-of-the-art solutions (up to 14

Wearable devices such as smart glasses are transforming the way people interact with their surroundings, enabling users to seek information regarding entities in their view. Multi-Modal Retrieval-Augmented Generation (MM-RAG) plays a key role in supporting such questions, yet there is still no comprehensive benchmark for this task, especially regarding wearables scenarios. To fill this gap, we present CRAG-MM – a Comprehensive RAG benchmark for Multi-modal Multi-turn conversations. CRAG-MM contains a diverse set of 6.5K (image, question, answer) triplets and 2K visual-based multi-turn conversations across 13 domains, including 6.2K egocentric images designed to mimic captures from wearable devices. We carefully constructed the questions to reflect real-world scenarios and challenges, including five types of image-quality issues, six question types, varying entity popularity, differing information dynamism, and different conversation turns. We design three tasks: single-source augmentation, multi-source augmentation, and multi-turn conversations – each paired with an associated retrieval corpus and APIs for both image-KG retrieval and webpage retrieval. Our evaluation shows that straightforward RAG approaches achieve only 32

Recent advances in conversational AI have been substantial, but developing real-time systems for perceptual task guidance remains challenging. These systems must provide interactive, proactive assistance based on streaming visual inputs, yet their development is constrained by the costly and labor-intensive process of data collection and system evaluation. To address these limitations, we present a comprehensive framework with three key contributions. First, we introduce a novel data curation pipeline that synthesizes dialogues from annotated egocentric videos, resulting in ProAssist, a large-scale synthetic dialogue dataset spanning multiple domains. Second, we develop a suite of automatic evaluation metrics, validated through extensive human studies. Third, we propose an end-to-end model that processes streaming video inputs to generate contextually appropriate responses, incorporating novel techniques for handling data imbalance and long-duration videos. This work lays the foundation for developing real-time, proactive AI assistants capable of guiding users through diverse tasks.

An empirical study conducted during the year 2022-23 at KNK College of Horticulture, Mandsaur (MP), India investigated the impact of gamma irradiation on floral quality and post-harvest parameters of four gladiolus varieties (V1 : Arka Aayush, V2: Arka Pratham, V3 : Arka Kesar and V4 : Arka Tilak) using five gamma doses (G1: 0.0 kr, G2 : 1.25 kr, G3 : 2.25 kr, G4 : 3.25 kr and G5 : 4.25 kr) in a Factorial Randomized Block Design (FRBD). Results indicated that Arka Kesar excelled in various parameters, including diameter and length of florets, spike girth, spike length and flowering duration. While, Arka Aayush exhibited superior performance in terms of vase life. Gamma irradiation at 0.00 kr (control) positively influenced several parameters, such as floret diameter, floret length, spike girth, spike length and vase life. The dose of 1.25 kr was beneficial for flowering duration. The interaction between gamma irradiation and varieties significantly affected vase life. Specifically, Arka Pratham irradiated with 0.00 kr exhibited the longest vase life (12.82 days).

In this paper, we investigate the problem of "generation supervision" in large language models, and present a novel bicameral architecture to separate supervision signals from their core capability, helpfulness. Doppelgänger, a new module parallel to the underlying language model, supervises the generation of each token, and learns to concurrently predict the supervision score(s) of the sequences up to and including each token. In this work, we present the theoretical findings, and leave the report on experimental results to a forthcoming publication.

We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i.e. text, image, video, audio, IMU motion sensor), and generates textual responses. AnyMAL inherits the powerful text-based reasoning abilities of the state-of-the-art LLMs including LLaMA-2 (70B), and converts modality-specific signals to the joint textual space through a pre-trained aligner module. To further strengthen the multimodal LLM's capabilities, we fine-tune the model with a multimodal instruction set manually collected to cover diverse topics and tasks beyond simple QAs. We conduct comprehensive empirical analysis comprising both human and automatic evaluations, and demonstrate state-of-the-art performance on various multimodal tasks.

The present experiment was carried out at Bahadari research farm of College of Horticulture, Mandsaur (Madhya Pradesh) during rabi season of 2020-21 with an aim to find out the effect of different spacing and corm size on growth and corm production of gladiolus, using the three spacing’s (S1 30 × 30 cm, S2 30 × 20 cm and S3 20 × 20 cm) and three corm sizes (C1 <3.0 cm, C2 3.0-4.0 cm and C3 >4.0 cm). The experiment was laid out in Factorial Randomized Block Design (FRBD) with three replications. The result revealed that, the plant produced from wider spacing with larger corm size (30 × 30 cm + >4.0 cm) was superior in days taken to sprouting (9.07 days), number of sprouts per hill (3.07), plant height at 60 DAP (62 cm), number of leaves per hill at 60 DAP (20.73), length of longest leaf at 60 DAP (46.47 cm), width of longest leaf at 60 DAP (2.85 cm), number of corms per hill (3.47) and weight of corms per hill (71.20 g) at maturity stage.

The data analysis has revealed distinct performance trends among different aspects of gladiolus cultivation. Specifically, Arka Kesar, a gladiolus variety, demonstrated superior growth characteristics, excelling in terms of plant height, the length and width of the longest leaf at both 30 and 60 days after planting (DAP). On the other hand, Arka Tilak outperformed in the number of corms and cormels per plant. Furthermore, the application of gamma irradiation at a level of 1.25 kr was found to be advantageous for several growth parameters. It positively influenced plant height, the number of leaves per hill, the length and width of the longest leaf at both 30 and 60 DAP, as well as the number of corms and cormels per plant. In conclusion, the study suggests that the Arka Kesar variety, when subjected to 1.25 kr gamma irradiation, displayed significant superiority across multiple growth parameters in gladiolus cultivation in the Malwa region of Madhya Pradesh, India. However, for corm yield specifically, Arka Tilak irradiated with 1.25 kr demonstrated better performance. These findings provide valuable insights for optimizing gladiolus cultivation practices in the region.