arXiv AI
LumiXAI: A Modular Full-Stack Framework for Feature Attribution
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 10
Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework
arXiv:2608. 06909v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory.
arXiv Machine Learning
Jun 11
Bergson: An Open Source Library for Data Attribution
arXiv:2606. 11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applications including debugging undesirable model behavior and training dataset curation.
arXiv AI
Jul 28
Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations
arXiv:2607. 22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turns?
arXiv AI
Sep 7
Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization
The paper introduces CAMS, a Claim‑Anchored Multi‑Document Summarization framework that decomposes source documents into atomic claims, resolves provenance deterministically from verbatim quotes to token spans, clusters equivalent claims across documents, and rewrites summaries so each sentence ends with claim identifiers linking back to source spans. CAMS separates provenance (an invariant for each emitted sentence) from faithfulness (an objective encouraged by selection, rewriting, and verification). Evaluations on MultiNews, DiverseSumm, and zero‑shot WCEP show that CAMS matches strong baselines in summary quality while improving faithfulness and citation precision, raising attribution accuracy from 38% to 64% and reducing human verification time per claim by 3.4×.
arXiv Machine Learning
Jun 2
Interpreto: An Explainability Library for Transformers
arXiv:2512. 09730v3 Announce Type: replace-cross Abstract: Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs.
arXiv Computation and Language
Sep 1
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
MURANO is an open‑source framework that enables researchers to design, run, and reproduce mechanistic interpretability experiments on large language models. It unifies the five key stages—loading, recording, attribution, intervention, and evaluation—into composable pipeline steps that exchange named artifacts and use canonical addresses for interoperability. The authors demonstrate the framework with reproductions of existing studies and a sparse autoencoder case study, showing its practical applicability across disciplines.