arXiv Computation and Language
GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
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
Jul 9
Future Confidence Distillation in Large Language Models
arXiv:2607. 07626v1 Announce Type: cross Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability.
arXiv AI
3d ago
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment
The paper introduces CoT-Interpretability Alignment (CIA), a metric that quantifies how well a large language model’s chain-of-thought (CoT) explanations match its internal reasoning processes. Evaluated on two-hop question answering, hint intervention, and integer multiplication across three LLMs, the study finds limited alignment (44.8–75.9%) and demonstrates that post‑training with a reward combining task accuracy and parametric faithfulness can substantially improve CoT faithfulness without sacrificing accuracy. The authors provide a framework for auditing CoT faithfulness and a pathway to making explicit reasoning more trustworthy, with code and data publicly available.
arXiv AI
Aug 11
Beyond Questions: Evaluating LLM's Knowledge Expression
arXiv:2605. 26937v2 Announce Type: replace-cross Abstract: Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood.
arXiv AI
Aug 20
From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning
The paper introduces VAKE, a two‑stage reinforcement‑learning framework that activates latent factual knowledge in large language models. In the Priming stage, the model explicitly inserts bridging triples into an insufficient subgraph, guided by rewards from a frozen model’s answers. The Reasoning stage then trains the model to answer from the original input, demonstrating that the elicitation capability transfers to implicit reasoning and consistently outperforms baselines across multiple benchmarks and model sizes.
arXiv AI
Aug 11
Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings
arXiv:2508. 17092v2 Announce Type: replace-cross Abstract: Knowledge Tracing (KT) aims to predict a student's future performance based on their sequence of interactions with learning content.
arXiv AI
Aug 11
RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning
arXiv:2604. 16694v2 Announce Type: replace Abstract: Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference latency and computational overhead.