arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.
arXiv:2608. 03291v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process.
arXiv:2608. 13604v1 Announce Type: new Abstract: Detection of misunderstanding is an urgent problem to solve because communication has moved away from real-time, in-person interaction and is increasingly handled by AI-mediated channels.
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:2606. 21678v2 Announce Type: replace-cross Abstract: Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal reasoning.
arXiv:2606. 05403v1 Announce Type: new Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
arXiv:2606. 31892v1 Announce Type: cross Abstract: "Any fool can know; the point is to understand.
arXiv:2606. 08532v5 Announce Type: replace Abstract: Modern artificial intelligence excels at prediction but cannot explain.
arXiv:2608. 11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists.
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv:2603. 25251v2 Announce Type: replace-cross Abstract: Explainable AI (XAI) methods are commonly evaluated using functional correctness metrics, sometimes termed faithfulness or fidelity, which estimate how closely an explanation reflects the model's reasoning.
Pragmatic language use requires reasoning about alternatives: the alternative expressions a speaker might have chosen, or the alternative interpretations a listener might entertain. Formal and computational models of pragmatics must therefore specify the sets of alternatives that interlocutors reason over, which is often done through manual specification.