Papers with ART

13 papers
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.
Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods use contrastive learning (CL) to learn effective sentence representations, but require extensive human annotation.
Approach: They propose a reinforcement learning approach for fine-tuning small-parameter LLMs to generate high-quality hard contrastive data without human feedback.
Outcome: The proposed method achieves state-of-the-art on seven semantic text similarity tasks.
Questions Are All You Need to Train a Dense Passage Retriever (2023.tacl-1)

Copied to clipboard

Challenge: Existing methods for dense retrieval require large supervised datasets with custom hard-negative mining and denoising of positive examples.
Approach: They propose a new corpus-level autoencoding approach for training dense retrieval models that does not require labeled training data.
Outcome: The proposed method matches or surpasses strong supervised performance levels on multiple QA benchmarks with no labeled training data or task-specific losses.
A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Existing benchmarks for testing audio modality of multimodal large language models focus on testing audio tasks in isolation.
Approach: They propose a new benchmark to assess multimodal large language models' ability to combine audio tasks.
Outcome: The proposed benchmarks show that multimodal models can solve problems that require reasoning over audio signals with satisfactory results.
ART: The Alternating Reading Task Corpus for Speech Entrainment and Imitation (2024.lrec-main)

Copied to clipboard

Challenge: The Alternating Reading Task (ART) Corpus is a collection of dyadic sentence readings for studying the entrainment and imitation behaviour in speech communication.
Approach: They propose to use dyadic sentence reading to study entrainment and imitation in speech communication.
Outcome: The proposed study includes three conditions and three subcorpora encompassing French-, Italian-, and Slovak-accented English.
Natural Language Reasoning in Large Language Models: Analysis and Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Argumentative reasoning presents unique challenges due to its reliance on context, implicit assumptions, and value judgments.
Approach: They propose a large-scale evaluation of LLMs' unconstrained natural language reasoning capabilities . they formalise a new strategy designed to evaluate argumentative reasoning in LLM .
Outcome: The proposed model performs better on a range of reasoning tasks than other models.
Automated Progressive Red Teaming (2025.coling-main)

Copied to clipboard

Challenge: Automated red teaming (ART) is effective but time-consuming, costly and lacks scalability.
Approach: They propose an automated red teaming framework that generates adversarial prompts to expose LLM vulnerabilities.
Outcome: The proposed framework explores and exploits LLM vulnerabilities through multi-round interactions.
ART: Attention-Regularized Transformers for Multi-Modal Robustness (2026.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to enhancing robustness are domain-specific or lack formal guarantees.
Approach: They propose a framework that enhances robustness across modalities by regularizing attention maps under adversarial perturbations.
Outcome: The proposed framework improves robustness across modalities and training on IMDB, QNLI, CIFAR-10, Cifar-100, and Imagenette.
The ART of LLM Refinement: Ask, Refine, and Trust (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations and self-improve?
Approach: They propose a reasoning with a refinement strategy called *ART: Ask, Refine, and Trust* that asks necessary questions to decide when an LLM should refine its output and uses it to affirm or deny trust.
Outcome: The proposed reasoning with a refinement strategy achieves a performance gain of +5 points over baselines on two multistep reasoning tasks.
Hint-Based Training for Non-Autoregressive Machine Translation (D19-1)

Copied to clipboard

Challenge: AutoRegressive Translation models have to generate tokens sequentially during decoding and thus suffer from high inference latency.
Approach: They propose to use hidden states and word alignments to help train NART models.
Outcome: The proposed model improves on the WMT14 En-De and De-En datasets but is faster in inference than the current models.
ART: rule bAsed futuRe-inference deducTion (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on language-based premises and deduce valid conclusions from visual observations.
Approach: They propose a rule-based deductive reasoning task that uses video to deduce the correct future event . they use commonsense knowledge to annotate video and a strong baseline to conduct reasoning .
Outcome: Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations . ART is a method that rigorously follows a set of explicit constraints to deduce valid conclusions from empirical facts .
ART: Attention Replacement Technique to Improve Factuality in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to mitigate hallucinations in large language models are expensive and require significant resources.
Approach: They propose a training-free method that replaces uniform attention patterns in shallow layers with local attention patterns to reduce hallucinations.
Outcome: The proposed method reduces hallucinations across multiple LLM architectures.
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to red teaming are based on example-based evaluation, where a static list of specific prompts is used to define and measure "unsafe content"
Approach: They propose a new automated red teaming framework that shifts from example-based to policy-based evaluation that focuses on risk coverage, semantic diversity, and fidelity.
Outcome: The proposed method achieves superior, human-readable attacks against open-source and proprietary models even for unseen safety policies.

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