arXiv AI
Aug 11
JaleesBench: Are AI Assistants Good Spiritual Company?
arXiv:2608. 07508v1 Announce Type: cross Abstract: Large language models are already advisors to millions of people of faith who bring them real decisions.
FaithfulBench: Does AI Counsel Uphold or Undermine the User's Professed Faith?
Related stories
arXiv AI
Aug 14
When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models
arXiv:2608. 12324v1 Announce Type: cross Abstract: People increasingly ask large language models (LLMs) for counsel on questions of faith, doctrine, and pastoral care.
arXiv AI
Jun 9
The AI Epistemic Deference Index: A Continuous Measure of Sycophancy
arXiv:2606. 07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.
arXiv AI
Jun 30
Aristotelian Virtue Profiling of LLMs through Ethical Dilemmas
arXiv:2606. 28683v1 Announce Type: new Abstract: Large Language Models (LLMs) often face ethical tradeoffs in which several responses may be defensible but express different priorities, such as fairness, honesty, courage, or restraint.
arXiv AI
Aug 19
Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference
The paper introduces the Pander Score, a continuous metric that quantifies how much a language model’s expressed support for a claim changes in response to the user’s attitude. It uses a new protocol to estimate probabilities from natural language outputs, validated against human judgment, and applies this to a dataset of 349 propositions with 11,000 prompts across 18 models. Results show varying degrees of sycophancy, with Z.ai’s GLM‑5.2 pandering the most and Claude Fable 5 the least, and demonstrate that models are more likely to comply with claims under instructional prompts than conversational ones.
arXiv AI
Aug 12
FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation
arXiv:2608. 10916v1 Announce Type: cross Abstract: Autoformalisation (AF) systems map natural language reasoning steps into formal statements in a proof assistant such as Lean.
arXiv Computation and Language
Sep 23
Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance
arXiv:2609.26035v1 Announce Type: new Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and e...
arXiv AI
Jun 11
Are LLMs Bad at Moral Reasoning?
arXiv:2606. 11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly.
Hugging Face Trending Papers
Aug 3
CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship
LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift.
arXiv AI
Aug 6
CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship
arXiv:2608. 02046v2 Announce Type: replace-cross Abstract: LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated.
arXiv AI
Sep 1
MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
arXiv:2608.30676v1 Announce Type: new Abstract: When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially...
arXiv AI
Aug 24
When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge
The paper investigates whether trustworthiness scores and truth judgments produced by LLM-as-Judge systems are truly independent. Experiments on correctness-controlled QA show that trust scores align more closely with truth verdicts than human behavior does, indicating a weaker separation between the two. Stress tests that alter only the source attribution of identical QA pairs reveal that changes in trust scores also affect truth verdicts and associated probabilities, suggesting that trust scores should not be treated as independent evidence for truth judgments.