Research map / Large language models / Language, safety and interpretability
Context Aware Conversational Understanding for Intelligent Agents With a Screen
Vishal Naik, Angeliki Metallinou, Rahul Goel
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add screen-context features (keys, values) to BiLSTM (ablation) | non-context BiLSTM · Contextual test set intents and slots | micro-F1 | Improved |
| add screen-context features (ablation) | non-context BiLSTM · Non-contextual test set | micro-F1 | No clear effect |
| add screen-context features (ablation) | non-context BiLSTM · Contextual intents and slots | macro-F1 | Improved |
| end-to-end contextual BiLSTM instead of rule-based reranker (ablation) | non-context BiLSTM + reranker · Contextual test set | F1 | Improved |
| add value features to key features (ablation) | context-BiLSTM(keys) · Contextual test set | F1 | Improved |
| replace BiLSTM(keys,values) with CNN+BiLSTM(keys,values) (ablation) | context-BiLSTM(keys,values) · Contextual test set | F1 | No clear effect |
| shuffle value inputs between training epochs (ablation) | context-BiLSTM(keys,values) · Contextual test set | F1 | Improved |
| add ReLU after max pooling (ablation) | context-CNN+BiLSTM · Contextual test set | F1 | Improved |
Closest papers by meaning
- ContextAgent: Context-Aware Proactive LLM Agents with Open-world Sensory Perceptions (NeurIPS 2025 · similarity 0.85)
- ContextNav: Towards Agentic Multimodal In-Context Learning (ICLR 2026 · similarity 0.84)
- Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (ICLR 2025 · similarity 0.84)
- Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models (NeurIPS 2024 · similarity 0.84)
- Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction (AAAI 2026 · similarity 0.84)
- Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding (AAAI 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
