Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
cs.AI, cs.CL, cs.LG
Submitted: 2026-04-07
Updated: 2026-11-08
Terminology
Sources
- The Internal State of an LLM Knows When It's Lying
- Discovering Latent Knowledge in Language Models Without Supervision
- Mistral 7B
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- ConSens: Assessing context grounding in open-book question answering
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
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