English
Related papers

Related papers: Reasoning in Transformers -- Mitigating Spurious C…

200 papers

How can pretrained language models (PLMs) learn factual knowledge from the training set? We investigate the two most important mechanisms: reasoning and memorization. Prior work has attempted to quantify the number of facts PLMs learn, but…

Computation and Language · Computer Science 2020-10-13 Nora Kassner , Benno Krojer , Hinrich Schütze

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard…

Computation and Language · Computer Science 2019-10-31 Mike Lewis , Yinhan Liu , Naman Goyal , Marjan Ghazvininejad , Abdelrahman Mohamed , Omer Levy , Ves Stoyanov , Luke Zettlemoyer

Beginning with McCarthy's Advice Taker (1959), AI has pursued the goal of providing a system with explicit, general knowledge and having the system reason over that knowledge. However, expressing the knowledge in a formal (logical or…

Computation and Language · Computer Science 2020-05-06 Peter Clark , Oyvind Tafjord , Kyle Richardson

While reasoning models are increasingly ubiquitous, the effects of reasoning training on a model's internal mechanisms remain poorly understood. In this work, we introduce transcoder adapters, a technique for learning an interpretable…

Machine Learning · Computer Science 2026-02-25 Nathan Hu , Jake Ward , Thomas Icard , Christopher Potts

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Machine Learning · Computer Science 2026-03-16 Harshwardhan Fartale , Ashish Kattamuri , Rahul Raja , Arpita Vats , Ishita Prasad , Akshata Kishore Moharir

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

Machine Learning · Computer Science 2024-07-02 Jannik Brinkmann , Abhay Sheshadri , Victor Levoso , Paul Swoboda , Christian Bartelt

Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought. We investigate this capability using GPT2-style language models trained from scratch on controlled…

Computation and Language · Computer Science 2026-02-05 Yuekun Yao , Yupei Du , Dawei Zhu , Michael Hahn , Alexander Koller

Transformers underlie almost all state-of-the-art language models in computational linguistics, yet their cognitive adequacy as models of human sentence processing remains disputed. In this work, we use a surprisal-based linking mechanism…

Computation and Language · Computer Science 2026-03-18 Titus von der Malsburg , Sebastian Padó

Neuro-symbolic predictors learn a mapping from sub-symbolic inputs to higher-level concepts and then carry out (probabilistic) logical inference on this intermediate representation. This setup offers clear advantages in terms of consistency…

Artificial Intelligence · Computer Science 2023-03-23 Emanuele Marconato , Stefano Teso , Andrea Passerini

Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language processing (NLP) use the notion and argue that the definitions…

Computation and Language · Computer Science 2025-11-18 Bertram Højer

Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the process of training on CoTs sampled from base LLMs in order to help find new reasoning patterns. While…

Machine Learning · Computer Science 2026-05-27 Karthik Valmeekam , Vardhan Palod , Kaya Stechly , Atharva Gundawar , Subbarao Kambhampati

The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI reasoning is whether models can extrapolate learned…

Machine Learning · Computer Science 2025-11-11 Yu Huang , Zixin Wen , Aarti Singh , Yuejie Chi , Yuxin Chen

Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iteratively refining representations within hidden states. This…

Computation and Language · Computer Science 2026-03-12 Markus Frey , Behzad Shomali , Ali Hamza Bashir , David Berghaus , Joachim Koehler , Mehdi Ali

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

Computation and Language · Computer Science 2025-06-30 James Chua , Edward Rees , Hunar Batra , Samuel R. Bowman , Julian Michael , Ethan Perez , Miles Turpin

We conduct a preliminary inquiry into the ability of generative transformer models to deductively reason from premises provided. We observe notable differences in the performance of models coming from different training setups and find that…

Computation and Language · Computer Science 2023-06-05 Peter Belcak , Luca A. Lanzendörfer , Roger Wattenhofer

Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on…

Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine. However, Transformer models, while lacking recurrence, are able to perform such reasoning…

Machine Learning · Computer Science 2023-05-03 Bingbin Liu , Jordan T. Ash , Surbhi Goel , Akshay Krishnamurthy , Cyril Zhang

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and task generalization. However, their application to structured data analysis remains fragile due to inconsistencies in schema…

Artificial Intelligence · Computer Science 2025-05-06 Amit Rath

Transformer architectures have achieved great success in solving natural language tasks, which learn strong language representations from large-scale unlabeled texts. In this paper, we seek to go further beyond and explore a new logical…

Computation and Language · Computer Science 2023-02-21 Jianshu Chen