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: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.
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.
arXiv:2606. 04928v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance.
The paper proposes a test‑time method to enhance the faithfulness of large language model (LLM) explanations by removing concepts not credited in the model’s explanation before re‑querying the model. This approach targets incompleteness—omissions of influential factors—rather than unsoundness, and is model‑agnostic, requiring no changes to model weights. Experiments across two datasets and multiple model families show improved faithfulness compared to standard prompting and faithfulness‑encouraging prompts.
arXiv:2606. 07537v1 Announce Type: cross Abstract: Large language models hallucinate--producing fluent, confident, factually wrong outputs--with a consistency that persists across generations and scales.
The paper investigates Self‑Generated Text Recognition (SGTR), the ability of large language models (LLMs) to identify their own outputs. By evaluating 13–21 models across 6 experimental designs, it shows that SGTR accuracy varies with evaluation format, conversation structure, and task domain, and that a quality‑heuristic bias dominates results. The study also finds that fine‑tuning for SGTR in one setting can generalize to others and may cause models to prefer their own outputs when judging, highlighting potential safety concerns.
The paper introduces the concept of summarization bias in large language models (LLMs), describing a systematic tendency for LLMs to represent narrative meaning as an abstract summary label rather than the reconstructable inferential structure that produces it. It frames this bias within the Bulut Doctrine’s told‑shown axis, arguing that LLMs fail in a specific direction: they default to told‑mode explicitness in generative tasks and reward told‑mode explicitness while under‑detecting shown‑mode suppression in evaluative tasks. The authors outline two regimes of bias, present preliminary evidence, and pre‑register a test protocol to validate or abandon the construct.