Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reasoning failures persist, occurring even in seemingly simple scenarios. To systematically understand and address these shortcomings, the authors of the paper present the first comprehensive survey dedicated to reasoning failures in LLMs.
The authors introduce a novel categorization framework that distinguishes reasoning into embodied and non-embodied types, with the latter further subdivided into informal (intuitive) and formal (logical) reasoning. In parallel, the authors classify reasoning failures along a complementary axis into three types: fundamental failures intrinsic to LLM architectures that broadly affect downstream tasks; application-specific limitations that manifest in particular domains; and robustness issues characterized by inconsistent performance across minor variations. For each reasoning failure, the authors provide a clear definition, analyze existing studies, explore root causes, and present mitigation strategies.
Read more…
Source: ARXIV, Cornell University
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- New Tradecraft of Iranian Cyber Group Aria Sepehr Ayandehsazan aka Emennet Pasargad
October 30, 2024
The Federal Bureau of Investigation (FBI), U.S. Department of Treasury, and Israel National Cyber Directorate are releasing this Cybersecurity Advisory (CSA) to warn network defenders of new cyber tradecraft of the Iranian cyber group Emennet Pasargad, which has been operating under the company name Aria Sepehr Ayandehsazan (ASA) and is known by the private sector ...
- How Israel harnesses technology to advance its offensive in Middle East
October 7, 2024
In September, thousands of pagers exploded across Lebanon in what seemed to be a sophisticated attack planned months in advance by Israel, turning the spotlight on the country’s cyber capabilities and its use of artificial intelligence (AI) in warfare. Since October 7, 2023, Israel has shown no signs of slowing down its military rampage on multiple ...
- Identifying Rogue AI
September 19, 2024
For many – certainly given the share price of some leading proponents – the hype of AI is starting to fade. But that may be about to change with the dawn of agentic AI. It promises to get humanity far closer to the ideal of AI as an autonomous technology capable of goal-oriented problem solving. But ...
- AI search is going to change marketing… are you prepared?
September 3, 2024
OpenAI, the company behind ChatGPT, has announced they are building a search engine. It’s a move that begs two simple questions: is Google at risk and will this change how you market your business? The answer is yes to both. AI search engines aren’t new. Perplexity is an AI search engine with a valuation of over ...
- Cyber security in critical industries: challenges, solutions, and the road ahead
August 30, 2024
In an era of rapid digital transformation, cyber security has emerged as a paramount concern, particularly for critical industries such as energy, healthcare, and transportation. As we approach the IET’s Cyber Security for Critical Industries 2024 conference, it is essential to delve into the latest cyber security challenges and explore how building resilient and responsive ...
- Rogue AI is the Future of Cyber Threats
August 15, 2024
Yoshua Bengio, regarded as one of the “godfathers” of artificial intelligence, has likened the now-ubiquitous technology to a bear. When we teach the bear to become smart enough to escape its cage, we no longer control it. All we can do after that is try to build a better cage. This should be our goal with ...