Limitations of Language Models in Arithmetic and Symbolic Induction (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown that large pretrained Language Models (LMs) can perform remarkably well on a range of NLP tasks but they have limitations on basic symbolic manipulation tasks such as copy, reverse, and addition. |
| Approach: | They propose to use explicit positional markers, fine-grained computation steps, and LMs with callable programs to teach large pretrained Language Models. |
| Outcome: | The proposed model can perform 100% accuracy in OOD and repeating symbols. |
Similar Papers
oLMpics-On What Language Model Pre-training Captures (2020.tacl-1)
Copied to clipboard
| Challenge: | Recent success of pre-trained language models has spurred widespread interest in their capabilities. |
| Approach: | They propose an evaluation protocol that includes zero-shot evaluation and no fine-tuning . they propose to compare the learning curve of a fine- tuned LM to the learning of multiple controls . |
| Outcome: | The proposed evaluation protocol compares the learning curve of a fine-tuned LM to the learning of multiple controls. |
Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) excel at complex math but fail on basic addition, raising the question of whether they grasp rules or are merely reproducing patterns. |
| Approach: | They systematically probe LLMs’ understanding of two-integer addition by testing three crucial properties: commutativity (A+B=B+A), representation invariance via symbolic remapping and consistent accuracy scaling with operand length. |
| Outcome: | The proposed models achieve high numeric accuracy but fail basic addition tasks. |
Language Models Implement Simple Word2Vec-style Vector Arithmetic (2024.naacl-long)
Copied to clipboard
| Challenge: | a primary criticism of language models is their inscrutability. |
| Approach: | They propose to use a vector arithmetic style mechanism to solve relational tasks . they find that this mechanism is specific to tasks that require retrieval from pretraining memory . |
| Outcome: | The proposed model reduces to a simple additive update for a variety of tasks . the findings contribute to proving that the models are interpretable and reliable . |
Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work showed limited success in probing numeric values from models’ representations, indicating that these errors can be attributed to the inherent unreliability of distributionally learned embeddings in representing exact quantities. |
| Approach: | They propose a probing technique that decodes numeric values from input embeddings with near-perfect accuracy across a range of open-source LMs. |
| Outcome: | The proposed probing technique decodes numeric values from input embeddings with near-perfect accuracy across a range of open-source LMs. |
Language Models Learn Universal Representations of Numbers and Here’s Why You Should Care (2026.acl-long)
Copied to clipboard
Michal Štefánik, Timothee Mickus, Marek Kadlčík, Bertram Højer, Michal Spiegel, Raúl Vázquez, Aman Sinha, Josef Kuchař, Philipp Mondorf, Pontus Stenetorp
| Challenge: | Prior work has shown that large language models (LLMs) often converge to accurate input embedding for numbers, based on sinusoidal representations. |
| Approach: | They show that large language models often converge to accurate input embedding for numbers, based on sinusoidal representations. |
| Outcome: | The proposed representations are strikingly systematic, and are interchangeable in a large swathe of experimental setups. |
Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks (2024.acl-short)
Copied to clipboard
| Challenge: | Despite the generality and far-reaching consequences of large language models, there are still significant limitations making it difficult to apply them to certain tasks. |
| Approach: | They show that large language models can perform arithmetic tasks more robustly when conditioned on all of the correct higher-order digits. |
| Outcome: | The proposed model can predict the first digit of n-digit by m-digit multiplication without chain of thought reasoning, but in practice it fails to correctly predict the last digit on n digit by 1-digit multiplikation . |
Working Memory Identifies Reasoning Limits in Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using large language models, we examine the limitations of their cognitive capabilities and their working memory. |
| Approach: | They examine the limitations of large language models from a scaling perspective . they also assess various prompting strategies, revealing their diverse impacts on LLM performance. |
| Outcome: | The proposed models perform poorly on n-back tasks and on prompting strategies. |
Lower Bounds on the Expressivity of Recurrent Neural Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies of the representational capacity of neural LMs have focused on their ability to recognize formal languages. |
| Approach: | They propose to connect recurrent neural networks (RNNs) as classifiers to finite-state automatas (FSAs) and a probabilistic FSA to characterize their representational capacity. |
| Outcome: | The proposed models can express arbitrary regular LMs with linearly bounded precision. |
A Comprehensive Evaluation of Inductive Reasoning Capabilities and Problem Solving in Large Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Inductive reasoning is fundamental to both human and artificial intelligence. |
| Approach: | They evaluated the inductive reasoning abilities of current Large Language Models (LLMs) and their performance on symbolic tasks. |
| Outcome: | The proposed models fail on symbolic tasks and show that chain-of-thought prompts help them by decomposing the problem-solving process, but the LLMs learn limitedly. |
What do Large Language Models Learn beyond Language? (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Pretraining on text confers models with useful ‘inductive biases’ for non-linguistic reasoning. |
| Approach: | They investigate whether pre-training on text confers these models with helpful ‘inductive biases’ for non-linguistic reasoning. |
| Outcome: | The proposed models outperform non-pretrained models on 19 non-linguistic tasks and show that they retain inductive biases even when training on multi-lingual text and computer code. |