Best Open Source Question Answering Systems (2026)

🔥 Trending this week in Question Answering

Question Answering

Tencent/WeKnora🔥 active

▲ +725 ★ this week

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

🔍 Search & Retrieval

GoOtherupdated Nov 9, 2026

GitHub ↗★ 37.3K⑂ 5.2K

Question Answering

SciPhi-AI/R2R

▲ +29 ★ this week

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

🔍 Search & Retrieval🤖 Language Models

PythonMITupdated Nov 7, 2025

GitHub ↗★ 8.1K⑂ 654

Question Answering

onyx-dot-app/EnterpriseRAG-Bench

▲ +18 ★ this week

Dataset and benchmark for RAG on company internal documents.

🔍 Search & Retrieval🤖 Language Models

OtherMITupdated Sep 3, 2026

GitHub ↗★ 631⑂ 75

Question Answering

PolyU-VCLab/OmniCompass🔥 active

▲ +14 ★ this week

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Pythonno licenseupdated Nov 10, 2026

GitHub ↗★ 151⑂ 1

Question Answering

SylphAI-Inc/AdalFlow

▲ +8 ★ this week

AdalFlow: The library to build & auto-optimize LLM applications.

🔍 Search & Retrieval📝 Text Summarization🧠 Natural Language Processing

PythonMITupdated Nov 1, 2026

GitHub ↗★ 4.2K⑂ 391

Question Answering

PaddlePaddle/PaddleNLP

▲ +6 ★ this week

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

🧠 Natural Language Processing💖 Sentiment Analysis⛏️ Information Extraction

PythonApache-2.0updated May 23, 2026

GitHub ↗★ 13K⑂ 3K

📄 New research on Question Answering

📄 arXiv:2611.14515 · cs.LG45h ago

AutoScaffold: AI-Guided Scaffolding for Reinforcement Learning of Language Models

Zijian Zhang, Rizhen Hu, Jiangweizhi Peng +4

Reinforcement learning with verifiable rewards (RLVR) produces rich training experience, yet outcome rewards reduce each attempt to a single number and leave most of this information unused. Training-time scaffolds, such as strategies or hints added to the prompt during training, offer a natural way to turn this information into guidance, but their design and adaptation are largely left to humans and tailored to specific domains. We introduce AutoScaffold, a unified AI-for-AI framework that turns a student's training experience into adaptive scaffolds, with minimal domain-specific information and no human intervention during training. A frozen teacher periodically examines this experience, diagnoses bottlenecks, and designs scaffolds in two forms: (i) strategies shared across a class of tasks and (ii) hints for individual hard tasks, adjusting the content and amount of support as the student learns. The scaffolds are removed at evaluation. We apply the same framework to ALFWorld, search-based QA, mathematical reasoning, and GPU kernel generation. When evaluated without scaffolds, students trained with AutoScaffold outperform those trained with the corresponding RL baselines in all four domains, with gains of 7.2 points in ALFWorld success and 4.0 points in average QA exact match. On GPU kernel generation, AutoScaffold increases the fraction of tasks with a correct kernel that runs faster than the PyTorch reference by up to 5.0 points. On math, our student surpasses QuestA's reported accuracy using approximately one-third as many student training steps. Analyses show that the teacher identifies a different failure in each task class and shifts its scaffolds from step-by-step workflows to targeted fixes as the student improves, and that its revised scaffolds help the student learn more than keeping the previous scaffold or using no scaffold.▼ more

❓ Question Answering🤖 Language Models

arXiv ↗PDF ↗

📄 arXiv:2611.14100 · cs.CL2d ago

Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders

Mikhail Kulakov, Ruslan Solikhov, Ivan Bondarenko

💬 7 pages, 3 figures. Published in the Proceedings of the Third Workshop on Uncertainty-Aware NLP (UncertaiNLP 2026), Budapest, Hungary. Presented as a poster at the workshop

We present our system for the SHROOM-visions 2026 shared task on character-level hallucination span detection in image-conditioned vision-language model (VLM) responses, evaluated across English, French, Italian, and Chinese. The detector is built on a frozen Gemma-4-12B-it backbone with trainable LoRA adapters (approximately 10.7M parameters). Because the backbone is a causal decoder, hidden states read from a single copy of an answer cannot attend to subsequent tokens; we therefore repeat the candidate answer within one prompt and extract features from its second occurrence, giving every position approximate bidirectional context in a single non-autoregressive pass. A character-level locator combines intermediate hidden states to predict hallucination probabilities, BIO boundaries, and a response-level abstention score, while separate language-specific classifiers assign one of five hallucination types to each predicted span. On the closed test set, our system reaches a macro-averaged character IoU of 0.4404, more than doubling the official baseline (0.1854), and ranks 5th-6th on IoU across the four languages. On the English tuning split, controlled ablations attribute a gain to the repeated answer that is comparable to that of LoRA adaptation (its held-out gain is smaller and concentrated on hallucinated answers), and they show that the detector relies on the image-answer pairing: shuffling images across examples drives IoU down to the level of the predict-nothing floor or below it in every language. In deployments where the same Gemma-4-12B-it model also generates answers, its base weights can be reused, making the approach practical for local question-answering systems that cannot run a separate verifier.▼ more

❓ Question Answering🤖 Language Models

arXiv ↗PDF ↗

📄 arXiv:2611.13426 · cs.CL3d ago

BioMem: Agentic Memory for Biomedical LLM Agents

Mingchen Li, Yongkang Xiao, Rumeng Li +2

Large language models (LLMs) have demonstrated considerable potential in biomedical applications, while agentic memory systems have emerged as a promising approach to preserving and utilizing information across tasks and interactions. However, a fundamental question remains: how effectively and reliably do these systems retain, retrieve, update, and utilize biomedical information? In this study, we systematically investigate agentic memory in the biomedical domain, focusing on task effectiveness, retrieval quality, information fidelity, and long-term robustness. We evaluate five memory approaches across four LLMs in three representative settings: biomedical knowledge reasoning, clinical prediction, and long-term conversational memory. Our analyses reveal how memory construction, evidence relevance, and conversational history shape downstream biomedical performance, highlighting the distinct challenges of retrieving relevant information, preserving its fidelity, and effectively utilizing it for reasoning. Building on these findings, we introduce Hybrid Memory Retrieval and Utilization (HMRU), a training-free framework that jointly enhances evidence accessibility and task-aware utilization to improve biomedical reasoning and long-term conversational memory. HMRU achieves an average relative improvement of 8.6% across biomedical question-answering and conversational memory benchmarks, with additional gains in selected clinical prediction tasks. It further reduces conversational answer errors by 24.9% and closes 48.0% of the performance gap to full-context inference. Our findings provide a systematic characterization of biomedical agentic memory and practical insights into developing more effective and reliable memory-augmented LLM systems.▼ more

❓ Question Answering🔍 Search & Retrieval🤖 Language Models

arXiv ↗PDF ↗

📄 arXiv:2611.12407 · cs.CL3d ago

BDBBQ: A Human-AI Collaborative Benchmark for Bengali Social Bias in LLMs

Provat Saha, Ashika Habib Khan, Tahseen Tanha +2

Despite growing attention to social bias in large language models (LLMs), existing bias benchmarks provide limited coverage of culturally grounded evaluation in Bengali, particularly within Bangladesh's sociocultural context. To address this gap, we develop a bilingual extension of BanglaBBQ comprising 61,312 question-answering instances across 12 social categories in English and Bengali. The benchmark incorporates balanced answer permutations, contrasting question framings, and both ambiguous and disambiguated contexts to systematically examine model performance and stereotype-aligned bias across languages. We validate the dataset through structural checks, 220 statistical tests, and expert annotation of 150 instances by four annotators, achieving strong inter-annotator agreement (Fleiss' \k{appa}=0.8349). We evaluate eight LLMs across 490,496 instances and identify five key findings. First, disambiguated contexts yield substantially greater accuracy improvements in Bengali (+36.59 percentage points) than in English (+17.71). Second, all evaluated models exhibit lower accuracy in Bengali, although Mistral-Nemo shows the smallest cross-lingual accuracy gap (5.12 percentage points). Third, stereotype-aligned bias exhibits language and model dependent variation, increasing in Bengali for Gemma 2 9B but decreasing for Mistral-Nemo. Fourth, higher accuracy does not necessarily correspond to lower stereotype-aligned bias. Finally, bias varies considerably across social categories, with Qwen 2.5 7B exhibiting stronger stereotype alignment in Bengali for Politics and Physical Appearance. These findings demonstrate that cross-lingual performance and social bias are distinct dimensions of LLM behavior and underscore the importance of culturally grounded, language-sensitive benchmarks for evaluating fairness beyond English-centric settings.▼ more

❓ Question Answering🤖 Language Models

arXiv ↗PDF ↗

All new research →

Natural Language Processing2,559 Search & Retrieval1,485 Language Models1,375 Named Entity Recognition296 Text Classification264 Sentiment Analysis232

🔥 Trending this week in Question Answering

Tencent/WeKnora🔥 active

PolyU-VCLab/OmniCompass🔥 active

Top 30 question answering systems by stars

Tencent/WeKnora🔥 active

JohnSnowLabs/spark-nlp🔥 active

InternScience/GraphGen🔥 active

📄 New research on Question Answering

Related categories