llm-kb
← Back to research
Paper

NL-PAC paper introduces framework for handling specification ambiguity in LLM supervision

A new arXiv paper proposes NL-PAC, a framework that addresses specification ambiguity when LLMs provide labels or evaluations from natural language instructions. The framework uses a fixed model's thresholded decoding law to define admissible labels and candidate targets, showing that additional labels reduce sampling error but cannot resolve identification problems from ambiguous specifications.

0 engagement·1 source·Thu, Jul 9, 2026, 09:53 PM
The paper, titled 'NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision,' was posted on arXiv on 2026-07-09. It formalizes a problem where a natural language specification admits multiple readings, and the supervision channel does not reveal which reading is operative. The authors introduce NL-PAC, which leverages a fixed model's thresholded decoding law to define admissible labels and candidate targets. A key result is that the probability that multiple labels are admissible equals the diameter of the pointwise-admissible target class. This work is relevant for practitioners using LLMs for data labeling, evaluation, and feedback, as it highlights fundamental limits of scaling labels under ambiguous specifications.

Entities

arXiv(tool)NL-PAC(concept)

Related

PaperFri, Jul 10, 2026, 09:31 AM

Researchers identify asymmetric generalization problem in LLM unlearning benchmarks

A new arXiv paper argues that existing machine unlearning benchmarks for LLMs suffer from under-forgetting and over-forgetting due to an asymmetric generalization problem. The authors propose that evaluation must cover diverse query formulations of target facts to reliably measure knowledge removal while preserving unrelated capabilities.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 01:45 PM

Self-Guided Test-Time Training Improves Long-Context LLM Accuracy

A new arxiv paper proposes Self-Guided Test-Time Training (SG-TTT) to improve long-context utilization in LLMs without requiring labeled data. The method uses the model's own predictions to generate pseudo-labels for fine-tuning on the test context, addressing accuracy degradation in long inputs. This approach is more efficient than full TTT and shows promise for practical deployment.

0 engagement·1 source·arxiv
arXiv
PaperSun, Jul 12, 2026, 06:04 PM

Mechanistic interpretability researchers apply causality theory to LLMs

Researchers are applying causality theory from the paper 'Causal Abstraction for Interpretability' (arXiv:2301.04709) to understand LLM internals. This approach aims to identify causal mechanisms within models, moving beyond correlation-based analysis.

128 engagement·1 source·hackernews
PaperFri, Jul 10, 2026, 03:16 PM

Rashomon Explanation Set with LLMs Challenges Accuracy-Explainability Trade-off

A new arXiv paper introduces the Rashomon Explanation paradigm, which uses large language models to generate a set of faithful explanations for machine learning predictions. The authors argue that the perceived trade-off between accuracy and explainability is an artifact of treating explanation and prediction separately, and that coupling them can improve both. This work offers a practical path for building models that are both accurate and interpretable.

0 engagement·1 source·arxiv
arXiv
PaperTue, Jul 7, 2026, 05:43 PM

Researchers identify modality interference as root cause of full-duplex SLM degradation

A new paper on arXiv (July 7, 2026) presents a fine-grained analysis of optimization dynamics in full-duplex Spoken Language Models (SLMs), identifying severe modality interference as the root cause of knowledge degradation and compromised semantic integrity. The work aims to enable more natural and intelligent full-duplex SLMs.

0 engagement·1 source·arxiv
arXiv