When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
cs.AI, cs.CL, cs.LG
Submitted: 2026-02-12
Updated: 2026-11-01
Terminology
Sources
- Towards a Human-like Open-Domain Chatbot
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- DeepSeek-V3 Technical Report
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Hierarchical Selective Classification
- Why Language Models Hallucinate
- Qwen3 Technical Report
- Using Information Content to Evaluate Semantic Similarity in a Taxonomy
- Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering
- The Llama 3 Herd of Models
- LaMDA: Language Models for Dialog Applications
- A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
- A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
- Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
- Conditional validity of inductive conformal predictors
- Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents