The paper argues that feature attribution scores for generative language models lack a fixed meaning because each generated token is both output and input, leading to multiple distinct explanatory questions. It introduces the Attribution Contract framework, which explicitly defines the model score, fixed variables, target output, generation process, and eligible features, showing how these choices affect attribution outcomes. Experiments demonstrate that different contracts (e.g., local next-token vs. prompt-level) and model architectures (mixture-of-experts vs. masked-diffusion) yield markedly different attribution distributions, highlighting the need for careful contract specification.
arXiv:2605. 23080v2 Announce Type: replace Abstract: Feature attribution methods promise to identify which input features matter for a model output.
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
arXiv:2605.06295v2 Announce Type: replace Abstract: How can an arbitrary attribution method be generalized from first principles to capture interactions? We answer this with the metagame, a conceptua...
The paper proposes that two architectural assumptions—(1) attention and MLPs share a key‑value form <phi(S)>U, and (2) components read from an additive residual stream—are sufficient to answer three interpretability questions: component interaction, information routing, and token attribution. By treating these selections as a computational graph, the authors develop Unpack, a backward attribution method that validates interaction scores, recovered routes, and token attribution against established tests across models ranging from 160M to 6.9B parameters. The study also shows that contribution and causal effect can differ, with a recognizable signature in how components change when a task is removed.
arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.
arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.
arXiv:2603.13911v2 Announce Type: replace Abstract: A language model can give the wrong answer even when the correct answer is decodable from its intermediate states. To study this gap between decoda...
The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%. "whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."
arXiv:2605. 23393v2 Announce Type: replace-cross Abstract: Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction.
arXiv:2606. 05486v1 Announce Type: cross Abstract: Prompt ambiguity is a common source of failure in large language models, but is difficult to localize because it is a latent property of the prompt, while existing attribution methods are designed to explain observable outputs such as logits or generated tokens.
Circuit Oracle is an off‑the‑shelf large language model that, using a multi‑agent harness and task‑specific skills, can answer natural‑language questions about a target model by reading its attribution graph via tool calls. The system was evaluated on three safety‑relevant proxy tasks—detecting spurious features in probe circuits, eliciting hidden knowledge from taboo‑finetuned models, and suppression jailbreaking via feature‑level interventions—achieving 78.2 % accuracy on spurious‑feature detection and mixed results on the other tasks. In addition to task scores, Circuit Oracle produces pruned subgraphs and context‑specific feature explanations, which the authors release for further study.
arXiv:2610.17898v1 Announce Type: cross Abstract: Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predo...