arXiv Computation and Language
User Model Extraction via Belief Self-Distillation
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Aug 11
STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs
arXiv:2608. 08164v1 Announce Type: cross Abstract: Knowledge Distillation is a widely adopted technique in the training and fine-tuning of large language models (LLMs) enabling transfer of structured information and functional behavior from a large teacher model to a smaller student model while significantly reducing computational costs.
arXiv AI
Aug 24
Can LLMs Introspect? A Reality Check
The paper questions whether large language models (LLMs) truly introspect by critiquing recent studies that claim they can detect and report their internal states. It proposes two necessary conditions for genuine introspection: privileged access to internal representations and second‑order computation that distinguishes from first‑order task performance. Re‑examining two existing paradigms, the authors find that apparent introspective abilities can be explained by input‑based classifiers or generic anomaly detection, concluding that current evidence does not support metacognitive monitoring in LLMs.
Hugging Face Trending Papers
Jul 2
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels.
arXiv Machine Learning
Sep 11
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Negative Self-Distillation (NSD) is a new framework for improving large language models by encouraging them to diverge from their own flawed reasoning rather than imitate privileged solutions. Unlike On-Policy Self-Distillation, which can suppress uncertainty and exploratory behavior, NSD generates a question‑specific negative condition (e.g., a careless reasoner) and uses a dynamic gating mechanism to target only reasoning‑critical tokens for penalization. This approach preserves foundational language capabilities while consistently outperforming OPSD and other label‑free self‑bootstrapping reinforcement learning baselines.
arXiv AI
Jul 3
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
arXiv:2607. 02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain.
Hugging Face Trending Papers
Sep 10
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Negative Self-Distillation (NSD) is a new framework for improving large language models by encouraging them to diverge from their own flawed reasoning rather than imitate privileged solutions. Unlike On-Policy Self-Distillation (OPSD), which can suppress uncertainty and exploratory behavior, NSD generates a question‑specific negative condition (e.g., a careless reasoner) and pushes the student’s distribution away from it. A dynamic gating mechanism isolates reasoning‑critical tokens so that only behavioral flaws are penalized, preserving linguistic capabilities, and empirical results show NSD consistently outperforms OPSD and other label‑free self‑bootstrapping RL baselines.