Challenge: despite advances in transformers, their theoretical limitations in discrete reasoning remain a critical open problem.
Approach: They synthesize recent advances from three theoretical perspectives to clarify structural and computational barriers transformers face when performing symbolic computations.
Outcome: The proposed models excel at pattern matching and interpolation, but they face bottlenecks in communication and depth constraints.

Similar Papers

Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability Problems (2025.acl-long)

Copied to clipboard

Challenge: Transformer models exhibit minimal scale and noise invariance, along with limited vocabulary and number invariancy.
Approach: They probe the generalisation prowess of Transformer models with respect to the hitherto unexplored domain of numerical satisfiability problems.
Outcome: The proposed models exhibit minimal scale and noise invariance, along with limited vocabulary and number invariancy.
Circuit Complexity Bounds for RoPE-based Transformer Architecture (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies provide the circuit complexity bounds to Transformer-like architectures. position embedding has emerged as a crucial technique in modern large language models.
Approach: They propose to use position embedding to improve Transformer-like architectures by analyzing their circuits and analyzing the results.
Outcome: The proposed model is able to solve canonical tasks without embedding positional information.
The Parallelism Tradeoff: Limitations of Log-Precision Transformers (2023.tacl-1)

Copied to clipboard

Challenge: Existing work on transformers established their Turing completeness, albeit with assumptions like infinite precision and arbitrarily powerful feedforward subnets.
Approach: They propose to simulate transformers whose arithmetic precision is logarithmic in the number of input tokens by constant-depth logspace-uniform threshold circuits.
Outcome: The proposed model emerges from the transformer architecture’s high parallelizability, suggesting a potential inherent weakness of the scaling paradigm.
Saturated Transformers are Constant-Depth Threshold Circuits (2022.tacl-1)

Copied to clipboard

Challenge: Recent work shows that transformers with hard attention are limited in power, but hard attention is a strong assumption.
Approach: They propose a generalization of hard attention that captures attention patterns in transformers with saturated attention.
Outcome: The proposed generalization of hard attention more closely captures the attention patterns learnable in practical transformers.
Identifying the limits of transformers when performing model-checking with natural language (2023.eacl-main)

Copied to clipboard

Challenge: Recent studies have focused on transformer models’ ability to perform reasoning on text, but the above question has not been adequately answered.
Approach: They investigated the problem of model-checking with natural language to determine whether transformers can comprehend logical semantics in natural language.
Outcome: The proposed model-checking problem is suited to address this issue but is untouched in natural language inference research.
On the Ability and Limitations of Transformers to Recognize Formal Languages (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on LSTMs have not revealed their ability to model syntactic properties.
Approach: They propose to build a Transformers model for a subclass of counter languages and find that their learning mechanism strongly correlates with their construction.
Outcome: The proposed model generalizes well on counter languages and its learned mechanism correlates with it.
A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers (2024.naacl-long)

Copied to clipboard

Challenge: evaluating the generalisability of Transformers to out-of-distribution mathematical reasoning problems is a challenge for many open-source models.
Approach: They propose a method for generating and perturbing detailed derivations of equations at scale, aided by a symbolic engine, and compare their results to sequence classification tasks.
Outcome: The proposed framework outperforms GPT-4, GPT-3.5 and a canon of fine-tuned BERT models in classification tasks . perturbations to input reasoning can reduce their performance by up to 80 F1 points .
Can Transformers Reason in Fragments of Natural Language? (2022.emnlp-main)

Copied to clipboard

Challenge: Recent work on natural language inference has identified two strands of research .
Approach: They investigate whether neural networks have acquired logical principles from natural language . they use transformer-based models to detect valid inferences in controlled fragments of natural language.
Outcome: The proposed model overfits to superficial patterns in the data rather than acquiring the logical principles governing reasoning in natural language fragments.
SparseFlow: Accelerating Transformers by Sparsifying Information Flows (2024.acl-long)

Copied to clipboard

Challenge: SparseFlow is an efficient method to sparsify the dense information flows within transformers.
Approach: They propose a method to sparsify the dense pathways of token representations across all transformer blocks by parameterizing them to be sparse.
Outcome: The proposed method reduces computational costs by half on average without compromising task accuracy.
Understanding and Overcoming the Challenges of Efficient Transformer Quantization (2021.emnlp-main)

Copied to clipboard

Challenge: Recent advances in transformer quantization have shown remarkable improvement in many Natural Language Processing tasks and beyond.
Approach: They propose a novel quantization scheme for transformers that can be quantized to ultra-low bit-widths, leading to significant memory savings with a minimum accuracy loss.
Outcome: The proposed methods achieve state-of-the-art results on the GLUE benchmark using BERT, while preserving memory and accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations