paper-with-me

홈 › Papers

CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs

2026-02-09 · Longling Geng, Andy Ouyang, Theodore Wu, Daphne Barretto, Matthew John Hayes, Rachael Cooper, Yuqiao Zeng, Sameer Vijay, Gia Ancone, Ankit Rai, Matthew Wolfman, Patrick Flanagan, Edward Y. Chang arxiv

Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined. We introduce CTK, a diagnostic benchmark of 5,147 cases and growing, across 10 domains and all three levels of Pearl's Ladder of Causation. Unlike benchmarks that only score correctness, CTK reveals why a model failed by annotating causal rung, trap type, pressure sensitivity, refusal quality, and Utility-Safety tradeoffs. Its Sheep/Wolf taxonomy separates valid causal designs from inferential traps; paired neutral/pressure variants measure sycophantic drift through Bad Flip Rate; and Wise Refusal fields test whether a model identifies the missing information needed before endorsing a claim. CTK exposes failure modes hidden by aggregate accuracy: the Skepticism Trap, Rung Collapse under scaling, pressure-induced drift, Detection-Correction gaps, and counterfactual error modes. Rather than prescribing a correction method, it provides the diagnostic substrate for studying causal-reasoning failure profiles.

📄 PDF Abstract BibTeX arXiv:2602.08939

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment

2026-01-13 · Edward Y. Chang arxiv

Large language models increasingly fail in a way that scalar accuracy cannot diagnose: they produce a sound reasoning trace and then abandon it under social pressure or an authoritative hint. We argue that this is a cont…

SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes

2025-12-27 · Bharath Nunepalli arxiv

Retrieval-augmented generation (RAG) introduces a practical control problem: retrieval depth and generation behavior must be chosen per query to satisfy service-level objectives (SLOs) such as cost, refusal rate, and hal…

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

2026-07-31 · Xinyan Guan, Jiali Zeng, Chunlei Xin, Yaojie Lu 외 hf

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivations mislead users. We characterize this f…

Reinforcement Learning

Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs

2025-10-09 · Shuzhou Yuan, Ercong Nie, Yinuo Sun, Chenxuan Zhao 외 arxiv

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerat…

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

2026-07-23 · Zhetong Zhang, Honghao Fu, Miao Xu, Yiwei Wang 외 arxiv

As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful videos paired with benign queries achieve…