BridgeEQA creates a new benchmark and EMVR method for embodied agents to perform question answering on real-world bridge inspections using egocentric images and professional reports.
arXiv preprint arXiv:2404.16811 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
LongMemEval benchmarks long-term memory in chat assistants, revealing 30% accuracy drops across sustained interactions and proposing indexing-retrieval-reading optimizations that boost performance.
LPES uses per-layer scaling factors optimized by a genetic algorithm with Bézier curves to balance attention and improve long-context LLM performance by up to 11.2% on key-value retrieval.
A metadata-conditioned mT5 model trained on rule-augmented dialectal Arabic data produces translations that better match intended regional varieties than high-resource baselines, despite lower BLEU scores.
LLM graders achieve substantial human agreement on math and science MCAS items but vary on ELA, performing best as sources of formative narrative feedback rather than summative numerical scores.
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.
citing papers explorer
-
BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections
BridgeEQA creates a new benchmark and EMVR method for embodied agents to perform question answering on real-world bridge inspections using egocentric images and professional reports.
-
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
LongMemEval benchmarks long-term memory in chat assistants, revealing 30% accuracy drops across sustained interactions and proposing indexing-retrieval-reading optimizations that boost performance.
-
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
LPES uses per-layer scaling factors optimized by a genetic algorithm with Bézier curves to balance attention and improve long-context LLM performance by up to 11.2% on key-value retrieval.
-
Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection
A metadata-conditioned mT5 model trained on rule-augmented dialectal Arabic data produces translations that better match intended regional varieties than high-resource baselines, despite lower BLEU scores.
-
Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering
LLM graders achieve substantial human agreement on math and science MCAS items but vary on ELA, performing best as sources of formative narrative feedback rather than summative numerical scores.
-
The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.