question-answering

Tag

Cards List
#question-answering

Evaluating RAG Metrics in Applied Contexts: An Experiment, Its Findings and Its Limitations

arXiv cs.CL ↗ · 2026-07-09 Cached

This paper presents an empirical study evaluating RAG evaluation metrics from four libraries (Ragas, DeepEval, RAGChecker, Opik) by comparing them to human judgments and standard recall metrics, using a question-answering dataset created from business data.

0 favorites 0 likes
#question-answering

Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

arXiv cs.CL ↗ · 2026-07-09 Cached

This paper extends PubHealthBench into a retrieval-augmented setting and evaluates retrieval and generation choices for public health QA, showing hybrid retrieval improves accuracy and that smaller models with retrieval can match larger ones.

0 favorites 0 likes
#question-answering

RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation

arXiv cs.CL ↗ · 2026-07-08 Cached

This paper introduces RSF-GLLM, a framework that decouples differentiable graph reasoning from LLM generation to address the semantic gap in multi-hop knowledge graph question answering, achieving competitive performance with superior inference efficiency.

0 favorites 0 likes
#question-answering

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

arXiv cs.CL ↗ · 2026-07-03 Cached

Introduces MultAttnAttrib, a training-free method for multimodal attribution in long document QA, along with the MultAttrEval benchmark. It outperforms prompting-based methods and matches frontier models like GPT-5.4.

0 favorites 0 likes
#question-answering

From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators

arXiv cs.LG ↗ · 2026-07-01 Cached

Introduces MetaFlow, a method that trains large language models to generate zero-shot workflows for tasks by combining supervised fine-tuning and reinforcement learning with execution feedback, achieving strong generalization to untrained tasks and operator sets.

0 favorites 0 likes
#question-answering

mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health

arXiv cs.CL ↗ · 2026-06-30 Cached

This paper introduces MamaBench and MamaRetrieval, two benchmarks for evaluating medical retrieval-augmented generation in maternal, neonatal, and reproductive health, addressing gaps in existing QA and retrieval datasets.

0 favorites 0 likes
#question-answering

TriageRA-CCF: Source-Side Clinical Confidence and Coverage Signals for Adaptive Rank Budgeting in Medical LLMs

arXiv cs.CL ↗ · 2026-06-30 Cached

This paper proposes TriageRA-CCF, a method for adaptive rank budgeting in LoRA for medical question answering. It uses source-side signals (base-model confidence, clinical coverage, counterfactual proxy) to dynamically choose rank budgets, achieving modest accuracy gains on Qwen3-8B and Llama3.1-8B.

0 favorites 0 likes
#question-answering

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

arXiv cs.CL ↗ · 2026-06-30 Cached

AB-RAG is a training-free, backbone-agnostic framework that adaptively retrieves passages for question answering by estimating answer confidence, improving efficiency and accuracy across multiple backbones and datasets.

0 favorites 0 likes
#question-answering

PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs

arXiv cs.CL ↗ · 2026-06-30 Cached

PASTA is a novel framework for knowledge updating in LLMs that combines data augmentation, question-answering generation, and self-learning DPO to integrate factual information from news articles, achieving accuracy improvement from 0.02 to 0.82 while preserving general capabilities.

0 favorites 0 likes
#question-answering

Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering

arXiv cs.AI ↗ · 2026-06-29 Cached

Proposes OPI, an ontology-guided framework for multi-hop knowledge graph question answering that leverages a relation-centric ontology graph for bidirectional retrieval and iterative refinement, achieving state-of-the-art results on multiple benchmarks.

0 favorites 0 likes
#question-answering

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

arXiv cs.CL ↗ · 2026-06-29 Cached

This paper tests the assumption that LLMs judge better than they generate in in-context QA, finding generation accuracy exceeds self-evaluation on most benchmarks, with evaluation attending less to context. The findings challenge core assumptions in self-evaluation pipelines.

0 favorites 0 likes
#question-answering

Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026

arXiv cs.CL ↗ · 2026-06-29 Cached

This paper presents team HSA_CORAL's submission to the FinCausal 2026 shared task, comparing encoder-only, encoder-decoder, and decoder-only LLMs for extractive question answering of cause-effect relations in financial narratives. Fine-tuned GPT-4.1 Mini achieved top scores in the English subtask and third in Spanish.

0 favorites 0 likes
#question-answering

AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA

arXiv cs.AI ↗ · 2026-06-20 Cached

AgentFinVQA is a multi-agent pipeline for financial chart question answering that decomposes queries into planning, OCR, legend grounding, visual inspection, and verification steps, recording each step in a traceable Model Evaluation Packet. It achieves significant accuracy gains over zero-shot baselines while enabling on-premise deployment and auditability.

0 favorites 0 likes
#question-answering

Optimal Scheduling in a Question-Answering Forum of Knowledge Workers

arXiv cs.AI ↗ · 2026-06-20 Cached

This paper models a question-answering forum staffed by expert knowledge workers, studying optimal scheduling to maximize system capacity and stability.

0 favorites 0 likes
#question-answering

Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering

arXiv cs.CL ↗ · 2026-06-18 Cached

This paper introduces CADE, a framework for time-series question answering that maps each timestep directly into the LLM embedding space and uses a one-directional supervised contrastive loss to align time-series representations with frozen text anchors, outperforming existing baselines on the Time-MQA benchmark.

0 favorites 0 likes
#question-answering

Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning

arXiv cs.AI ↗ · 2026-06-16 Cached

Introduces IRTS-ToolBench, a benchmark of 1,700 questions for evaluating LLMs and AI agents on irregular time series question answering via tool-grounded reasoning, covering 10 task types across 13 domains.

0 favorites 0 likes
#question-answering

OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains

Hugging Face Daily Papers ↗ · 2026-06-12 Cached

OmniVideo-100K introduces an automated data engine with entity-anchored scripting and clue-guided QA generation to improve audio-visual reasoning and temporal consistency, achieving significant performance gains across multiple benchmarks.

0 favorites 0 likes
#question-answering

LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake

arXiv cs.CL ↗ · 2026-06-10 Cached

LakeQA is a new benchmark for exploratory question answering over a million-scale data lake, evaluating multi-hop reasoning and compositionality across text, tables, and knowledge graphs.

0 favorites 0 likes
#question-answering

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Hugging Face Daily Papers ↗ · 2026-06-09 Cached

Latent Memory introduces a compressed representation approach for external memory in question answering, reducing token consumption and storage requirements while maintaining competitive performance across text-only and multimodal benchmarks.

0 favorites 0 likes
#question-answering

Explicit Evidence Grounding via Structured Inline Citation Generation

arXiv cs.CL ↗ · 2026-06-08 Cached

This paper introduces FullCite, a framework for generating structured inline citations that link each claim to both its source document and specific evidence spans. Evaluated on three QA benchmarks (ASQA, BioASQ, ExpertQA), it finds that while LLMs are good at document-level attribution, they struggle with precise evidence span identification.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback