TABALIGN pairs a diffusion language model planner emitting binary cell masks with a trained attention verifier, raising average accuracy 15.76 points over strong baselines on eight table benchmarks while speeding execution 44.64%.
TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
FrontierFinance benchmark shows human financial experts outperform state-of-the-art LLMs by achieving higher scores and more client-ready outputs on realistic long-horizon tasks.
Hedge-Bench is a benchmark of 102 professional hedge fund tasks where frontier AI agents score below 16%.
TABQAWORLD improves multi-turn table QA by dynamically selecting multimodal representations and optimizing reasoning trajectories with metadata, delivering 4.87% accuracy gains over baselines and 33.35% latency reduction.
FinReasoning is a hierarchical benchmark that decomposes LLM financial research capabilities into semantic consistency, data alignment, and deep insight, revealing model-type differences in auditing versus insight generation.
OCC-RAG develops task-specialized SLMs (0.6B and 1.7B) via a new synthetic data pipeline for multi-hop reasoning and context faithfulness, claiming to match or exceed 2-6x larger general models on HotpotQA, MuSiQue, TAT-QA, ConFiQA, and MuSiQue-Un.
EvidenceLens is a visual analytics system that decomposes LLM financial answers into atomic claims and visualizes their multimodal evidence alignment, support gaps, and contradictions through a claim-evidence matrix and review-priority ranking.
citing papers explorer
-
From Table to Cell: Attention for Better Reasoning with TABALIGN
TABALIGN pairs a diffusion language model planner emitting binary cell masks with a trained attention verifier, raising average accuracy 15.76 points over strong baselines on eight table benchmarks while speeding execution 44.64%.
-
FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks
FrontierFinance benchmark shows human financial experts outperform state-of-the-art LLMs by achieving higher scores and more client-ready outputs on realistic long-horizon tasks.
-
Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning
Hedge-Bench is a benchmark of 102 professional hedge fund tasks where frontier AI agents score below 16%.
-
TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering
TABQAWORLD improves multi-turn table QA by dynamically selecting multimodal representations and optimizing reasoning trajectories with metadata, delivering 4.87% accuracy gains over baselines and 33.35% latency reduction.
-
FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting
FinReasoning is a hierarchical benchmark that decomposes LLM financial research capabilities into semantic consistency, data alignment, and deep insight, revealing model-type differences in auditing versus insight generation.
-
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
OCC-RAG develops task-specialized SLMs (0.6B and 1.7B) via a new synthetic data pipeline for multi-hop reasoning and context faithfulness, claiming to match or exceed 2-6x larger general models on HotpotQA, MuSiQue, TAT-QA, ConFiQA, and MuSiQue-Un.
-
EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering
EvidenceLens is a visual analytics system that decomposes LLM financial answers into atomic claims and visualizes their multimodal evidence alignment, support gaps, and contradictions through a claim-evidence matrix and review-priority ranking.