English
Related papers

Related papers: LINGOLY-TOO: Disentangling Reasoning from Knowledg…

200 papers

Evaluating the reasoning ability of language models (LMs) is complicated by their extensive parametric world knowledge, where benchmark performance often reflects factual recall rather than genuine reasoning. Existing datasets and…

Computation and Language · Computer Science 2026-03-11 Ken Gu , Advait Bhat , Mike A Merrill , Robert West , Xin Liu , Daniel McDuff , Tim Althoff

Ambiguity in natural language poses significant challenges to Large Language Models (LLMs) used for open-domain question answering. LLMs often struggle with the inherent uncertainties of human communication, leading to misinterpretations,…

Computation and Language · Computer Science 2024-11-20 Aryan Keluskar , Amrita Bhattacharjee , Huan Liu

Large language models can use chain-of-thought (CoT) to externalize reasoning, potentially enabling oversight of capable LLM agents. Prior work has shown that models struggle at two-hop question-answering without CoT. This capability is so…

Computation and Language · Computer Science 2025-11-25 Mikita Balesni , Tomek Korbak , Owain Evans

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…

Computation and Language · Computer Science 2026-05-19 Daniel Kaiser , Arnoldo Frigessi , Ali Ramezani-Kebrya , Benjamin Ricaud

Large language models (LLMs) have made remarkable progress in various natural language processing tasks as a benefit of their capability to comprehend and reason with factual knowledge. However, a significant amount of factual knowledge is…

Computation and Language · Computer Science 2024-08-23 Sirui Huang , Yanggan Gu , Xuming Hu , Zhonghao Li , Qing Li , Guandong Xu

Large Language Models (LLMs) perform well on standard reasoning and question-answering benchmarks, yet such evaluations often fail to capture their ability to handle long-tail, expertise-intensive knowledge in real-world professional…

Benchmark saturation and contamination have obscured genuine advances in reasoning for large language models (LLMs). We introduce NazoNazo Benchmark, a low-cost, renewable test built from Japanese children's riddles that demand…

Artificial Intelligence · Computer Science 2026-01-06 Masaharu Mizumoto , Dat Nguyen , Zhiheng Han , Jiyuan Fang , Heyuan Guan , Xingfu Li , Naoya Shiraishi , Yo Nakawake , Le Minh Nguyen

Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Monika Wysoczańska , Tom Monnier , Tomasz Trzciński , David Picard

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…

Computation and Language · Computer Science 2026-03-12 Prince Kumar , Rudra Murthy , Riyaz Bhat , Danish Contractor

Large language Models (LLMs) are usually used to answer questions, but many high-stakes applications (e.g., tutoring, clinical support) require the complementary skill of asking questions: detecting missing information, requesting…

Artificial Intelligence · Computer Science 2026-01-07 Rajeev Bhatt Ambati , Tianyi Niu , Aashu Singh , Shlok Mishra , Snigdha Chaturvedi , Shashank Srivastava

Formal mathematical reasoning remains a critical challenge for artificial intelligence, hindered by limitations of existing benchmarks in scope and scale. To address this, we present FormalMATH, a large-scale Lean4 benchmark comprising…

Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Autoformalisation helps…

Computation and Language · Computer Science 2025-10-15 Yupei Li , Philipp Borchert , Gerasimos Lampouras

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Computation and Language · Computer Science 2025-06-24 Kang Chen , Mengdi Zhang , Yixin Cao

While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results stem from genuine logical reasoning or semantic pattern matching against pre-training data.…

Machine Learning · Computer Science 2026-05-04 Lixing Li

Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully -- and lie detection -- classifying whether a…

Machine Learning · Computer Science 2026-03-11 Helena Casademunt , Bartosz Cywiński , Khoi Tran , Arya Jakkli , Samuel Marks , Neel Nanda

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

Large Language Models (LLMs) have shown impressive performance on various benchmarks, yet their ability to engage in deliberate reasoning remains questionable. We present NYT-Connections, a collection of 358 simple word classification…

Computation and Language · Computer Science 2025-02-26 Angel Yahir Loredo Lopez , Tyler McDonald , Ali Emami

Large language models (LLMs) have demonstrated solid zero-shot reasoning capabilities, which is reflected in their performance on the current test tasks. This calls for a more challenging benchmark requiring highly advanced reasoning…

Computation and Language · Computer Science 2023-06-05 Maksym Del , Mark Fishel

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Computation and Language · Computer Science 2025-10-17 Shiyuan Guo , Henry Sleight , Fabien Roger

Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to…

Artificial Intelligence · Computer Science 2026-05-19 Simon Henniger , Gabriel Poesia