Research map / Large language models / Language, safety and interpretability
Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use entailment relation memory (ERM) (ablation) | LMEDR · PersonaChat original | C.Score: 22.09 -> 25.31 | Helped |
| Use entailment relation memory (ERM) (ablation) | LMEDR · DSTC7-AVSD | CIDEr: 1.395 -> 1.403 | Helped |
| Use dialogue discourse memory (DDM) (ablation) | LMEDR · PersonaChat original | BLEU-4: 0.01406 -> 0.01561 | Helped |
| Use dialogue discourse memory (DDM) (ablation) | LMEDR · DSTC7-AVSD | BLEU-4: 0.482 -> 0.488 | Helped |
| Impose an orthogonal constraint between latent memories (ablation) | LMEDR · PersonaChat original | Hits@1: 88.8 -> 89.5 | Helped |
| Impose an orthogonal constraint between latent memories (ablation) | LMEDR · DSTC7-AVSD | BLEU-1: 0.782 -> 0.801 | Helped |
| Use LMEDR instead of P^2BOT | PersonaChat original · PersonaChat original | Hits@1: 81.9 -> 89.5 | Helped |
| Use LMEDR instead of DialogVED | DSTC7-AVSD · DSTC7-AVSD | CIDEr: 1.391 -> 1.403 | Helped |
| Use LMEDR instead of DialogVED | DSTC7-AVSD · DSTC7-AVSD | ROUGE-L: 0.636 -> 0.631 | Hurt |
| Use LMEDR instead of DialogVED | DSTC7-AVSD · DSTC7-AVSD | BLEU-4: 0.489 -> 0.488 | Hurt |
| Increase the number of interference responses to 14 | LMEDR response selection · PersonaChat original | Hits@1: 89.5(90.1) | Helped |
Closest papers by meaning
- Generating Persona Consistent Dialogues by Exploiting Natural Language Inference (AAAI 2020 · similarity 0.88)
- Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference (ICML 2023 · similarity 0.87)
- Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents (ICLR 2026 · similarity 0.86)
- From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue (AAAI 2024 · similarity 0.86)
- Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory (NeurIPS 2026 · similarity 0.86)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
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.