4 accepted papers
Recent advances in interpretability suggest that large language models (LLMs) implicitly encode signals in their generated text that enable self-recognition of their outputs. We demonstrate that this capability is reliable, even in low-entropy scenarios, and that it can be amplified through targeted…
Feature attribution has gained prominence as a tool for explaining model decisions, yet evaluating explanation quality remains challenging due to the absence of ground-truth explanations. To circumvent this, explanation-guided input manipulation has emerged as an indirect evaluation strategy, measur
Feature attribution explains machine decisions by quantifying each feature's contribution. While numerous approaches rely on exact gradient measurements, recent work has adopted gradient estimation to derive explanatory information under query-level access, a restrictive yet more practical accessibi…
Hallucination remains a critical failure mode of large language models (LLMs), undermining their trustworthiness in real-world applications. In this work, we focus on confabulation, a foundational aspect of hallucination where the model fabricates facts about unknown entities. We introduce a targete