English
Related papers

Related papers: Can We Trust AI Explanations? Evidence of Systemat…

200 papers

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully…

Can we trust the reasoning traces that large reasoning models (LRMs) produce? We investigate whether these traces faithfully reflect what drives model outputs, and whether models will honestly report their influence. We introduce Thought…

Artificial Intelligence · Computer Science 2026-03-24 Yijie Hao , Lingjie Chen , Ali Emami , Joyce Ho

In the context of AI-based decision support systems, explanations can help users to judge when to trust the AI's suggestion, and when to question it. In this way, human oversight can prevent AI errors and biased decision-making. However,…

Human-Computer Interaction · Computer Science 2025-08-12 Laura Spillner , Rachel Ringe , Robert Porzel , Rainer Malaka

Hint-based faithfulness evaluations have established that Large Reasoning Models (LRMs) may not say what they think: they do not always volunteer information about how key parts of the input (e.g. answer hints) influence their reasoning.…

Artificial Intelligence · Computer Science 2026-04-22 William Walden , Miriam Wanner

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that…

Computation and Language · Computer Science 2026-03-25 Richard J. Young

Although much research has focused on AI explanations to support decisions in complex information-seeking tasks such as fact-checking, the role of evidence is surprisingly under-researched. In our study, we systematically varied explanation…

Human-Computer Interaction · Computer Science 2026-01-19 Greta Warren , Jingyi Sun , Irina Shklovski , Isabelle Augenstein

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the…

Computation and Language · Computer Science 2025-10-15 Arash Marioriyad , Shaygan Adim , Nima Alighardashi , Mahdieh Soleymani Banghshah , Mohammad Hossein Rohban

Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI…

Human-Computer Interaction · Computer Science 2023-01-30 Helena Vasconcelos , Matthew Jörke , Madeleine Grunde-McLaughlin , Tobias Gerstenberg , Michael Bernstein , Ranjay Krishna

People supported by AI-powered decision support tools frequently overrely on the AI: they accept an AI's suggestion even when that suggestion is wrong. Adding explanations to the AI decisions does not appear to reduce the overreliance and…

Human-Computer Interaction · Computer Science 2021-02-22 Zana Buçinca , Maja Barbara Malaya , Krzysztof Z. Gajos

In human-AI interactions, explanation is widely seen as necessary for enabling trust in AI systems. We argue that trust, however, may be a pre-requisite because explanation is sometimes impossible. We derive this result from a formalization…

Artificial Intelligence · Computer Science 2025-03-03 Nghi Truong , Phanish Puranam , Ilia Testlin

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

Computation and Language · Computer Science 2023-12-12 Miles Turpin , Julian Michael , Ethan Perez , Samuel R. Bowman

The ability to discern between true and false information is essential to making sound decisions. However, with the recent increase in AI-based disinformation campaigns, it has become critical to understand the influence of deceptive…

Computers and Society · Computer Science 2022-10-18 Valdemar Danry , Pat Pataranutaporn , Ziv Epstein , Matthew Groh , Pattie Maes

Automated verbal deception detection using methods from Artificial Intelligence (AI) has been shown to outperform humans in disentangling lies from truths. Research suggests that transparency and interpretability of computational methods…

Human-Computer Interaction · Computer Science 2026-04-10 Riccardo Loconte , Merylin Monaro , Pietro Pietrini , Bruno Verschuere , Bennett Kleinberg

The right to AI explainability has consolidated as a consensus in the research community and policy-making. However, a key component of explainability has been missing: extrapolation, which describes the extent to which AI models can be…

Machine Learning · Computer Science 2022-04-29 Roozbeh Yousefzadeh , Xuenan Cao

A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for transparency and…

Human-Computer Interaction · Computer Science 2025-08-29 Mosh Levy , Zohar Elyoseph , Yoav Goldberg

Artificial intelligence (AI) comes with great opportunities but can also pose significant risks. Automatically generated explanations for decisions can increase transparency and foster trust, especially for systems based on automated…

Machine Learning · Computer Science 2021-12-03 Johannes Schneider , Christian Meske , Michalis Vlachos

Recent advances in AI models have increased the integration of AI-based decision aids into the human decision making process. To fully unlock the potential of AI-assisted decision making, researchers have computationally modeled how humans…

Human-Computer Interaction · Computer Science 2024-11-19 Zhuoyan Li , Ming Yin

Artificial Intelligence (AI) increasingly shows its potential to outperform predicate logic algorithms and human control alike. In automatically deriving a system model, AI algorithms learn relations in data that are not detectable for…

Artificial Intelligence · Computer Science 2022-10-12 Simon Daniel Duque Anton , Daniel Schneider , Hans Dieter Schotten

Extended-thinking models expose a second text-generation channel ("thinking tokens") alongside the user-visible answer. This study examines 12 open-weight reasoning models on MMLU and GPQA questions paired with misleading hints. Among the…

Computation and Language · Computer Science 2026-03-30 Richard J. Young

Effective human-AI collaboration requires humans to accurately gauge AI capabilities and calibrate their trust accordingly. Humans often have context-dependent private information, referred to as Unique Human Knowledge (UHK), that is…

Human-Computer Interaction · Computer Science 2025-11-07 Zenan Chen , Ruijiang Gao , Yingzhi Liang
‹ Prev 1 2 3 10 Next ›