Hierarchical Attention Generates Better Proofs (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have shown promise in formal theorem proving, but their token-level processing often fails to capture the inherent hierarchical nature of mathematical proofs.
Approach: They propose a regularization method that aligns LLMs’ attention mechanisms with mathematical reasoning structures and establishes a five-level hierarchy from foundational elements to high-level concepts.
Outcome: The proposed method improves proof success rates by 2.05% on miniF2F and 1.69% on ProofNet while reducing proof complexity by 23.81% and 16.50% respectively.

Similar Papers

Self-Attention Networks Can Process Bounded Hierarchical Languages (2021.acl-long)

Copied to clipboard

Challenge: Existing models that can process formal languages with hierarchical structure are limited in their performance.
Approach: They propose to use a subset of Dyck-k with depth bounded by D to train self-attention networks.
Outcome: The proposed model can process Dyck-(k, D) with depth bounded by D, which better captures the hierarchical structure of natural language.
ProofInfer: Generating Proof via Iterative Hierarchical Inference (2022.emnlp-main)

Copied to clipboard

Challenge: Existing proof generation models focus on generating several proof paths instead of a whole tree.
Approach: They propose a method that generates the proof tree via iterative hierarchical inference . they propose coding the proof as plain text without losing structure information .
Outcome: The proposed proof generation model significantly improves performance on widely-used datasets.
Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations (2025.acl-long)

Copied to clipboard

Challenge: Recent work has shown that the interaction of large language models (LLMs) with theorem provers (TPs) can help verify and improve the validity of NLI explanations.
Approach: They propose to use logical expressions to guide LLMs in generating structured proof sketches and to use them to improve their accuracy.
Outcome: The proposed strategies improve autoformalisation, syntactic errors and explanation refinement over the state-of-the-art model.
Visual Attention Reasoning via Hierarchical Search and Self-Verification (2026.acl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) often hallucinate due to fragile, linear reasoning and weak visual grounding.
Approach: They propose a framework that reformulates reasoning as a hierarchical search with self-verification and replaces linear Chain-of-Thought with a tree-search policy capable of backtracking to correct logical errors.
Outcome: The proposed framework outperforms state-of-the-art methods on hallucination and safety benchmarks.
Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are essential for performing complex multi-step reasoning tasks, such as multi-hop reasoning tasks.
Approach: They propose to use large language models to derive structured intermediate proof steps to improve their performance by using examples.
Outcome: The proposed models can derive correct proof steps with in-context learning.
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks (P19-1)

Copied to clipboard

Challenge: Claim verification is cumbersome and inefficient for human fact-checkers to find consistent pieces of evidence.
Approach: They propose an end-to-end hierarchical attention network that learns to represent coherent evidence and their semantic relatedness with the claim.
Outcome: The proposed model outperforms state-of-the-art models on three datasets . it is based on a coherence-based attention layer and entailment-based one .
ART: Adaptive Reasoning Trees for Explainable Claim Verification (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities.
Approach: They propose a hierarchical method for claim verification that uses a root claim and a pairwise tournament of its children to determine an argument's strength.
Outcome: The proposed method outperforms baseline methods on multiple datasets and shows that it is more reliable and clearer than existing methods.
Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding (2025.acl-long)

Copied to clipboard

Challenge: Existing studies show that Transformers can recognize hierarchical structures without a specific positional encoding.
Approach: They show that Transformers can generate hierarchical languages without a positional encoding . they also suggest that explicit positional encoders might have a detrimental effect on generalization .
Outcome: The proposed model can generate hierarchical languages with respect to model size without encoding .
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored.
Approach: They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs.
Outcome: The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs.
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps.
Approach: They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level.
Outcome: Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models.

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