Challenge: ambiguity in natural language is difficult to interpret due to large linguistic variability.
Approach: They propose to use a Prolog prover to extend neural networks with logic programming to solve multi-hop reasoning tasks over natural language.
Outcome: The proposed model outperforms baseline models on two question answering tasks and is competitive on the MedHop corpus.

Similar Papers

Complex Reasoning in Natural Language (2023.acl-tutorials)

Copied to clipboard

Challenge: Recent research shows that pretrained language models are often brittle for complex reasoning tasks.
Approach: They propose to use pre-trained language models to teach machines to reason over texts . they will review recent promising approaches to tackling complex reasoning tasks .
Outcome: This tutorial reviews promising approaches to complex reasoning tasks . it reviews the methods that can be used to augment models with robustness .
Neural Unification for Logic Reasoning over Natural Language (2021.findings-emnlp)

Copied to clipboard

Challenge: Automated Theorem Proving (ATP) is a computer program that can show that conjectures are logical consequences of a set of axioms.
Approach: They propose a transformer-based architecture for deriving conjectures given axioms . they propose 'neural unifier' and relative training procedure to train the model .
Outcome: The proposed architectures are able to answer queries with deep queries with a relatively low training time.
Can NLI Models Verify QA Systems’ Predictions? (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent question answering systems perform well on benchmark datasets, but are not always well-calibrated to spot spurious answers under distribution shifts.
Approach: They propose to use natural language inference to verify whether answers are correct . they leverage large pre-trained models and recent prior datasets to construct powerful question conversion and decontextualization modules.
Outcome: The proposed approach improves the confidence estimation of a QA model across different domains, evaluated in a selective QA setting.
From Sentences to Proof Trees: Leveraging Language Models for Structured Reasoning (2026.eacl-srw)

Copied to clipboard

Challenge: Multi-hop reasoning requires a chain of facts to reflect the reasoning behind the answer.
Approach: They propose an inference-guided prompting approach that performs well in natural language questions . they propose a neuro-symbolic approach to reasoning using large language models .
Outcome: The proposed model outperforms all prompting strategies and fine-tunes LLMs trained specifically for proof generation.
Explainable Multi-hop Verbal Reasoning Through Internal Monologue (2021.naacl-main)

Copied to clipboard

Challenge: Existing state-of-the-art language models do not make intermediate reasoning steps explicit . large pretrained language models such as BERT and RoBERTa have been successfully used in multi-hop reasoning problems .
Approach: They propose to decompose multi-hop reasoning problems into several simple ones and use natural language to guide intermediate reasoning hops.
Outcome: The proposed model can generate subgoals and perform inference in natural language at each reasoning step.
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.
Low-Resource Generation of Multi-hop Reasoning Questions (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to generate valid and fluent questions from text are limited and insufficient for training.
Approach: They propose to generate multi-hop reasoning questions from the raw text in a low resource circumstance by deducing over multiple relations on several sentences in the text.
Outcome: The proposed model can be applied to the task of machine reading comprehension and achieve significant performance improvements.
QA-NatVer: Question Answering for Natural Logic-based Fact Verification (2023.emnlp-main)

Copied to clipboard

Challenge: Recent work has focused on natural logic, which operates directly on natural language by capturing the semantic relation of spans between an aligned claim and its evidence via set-theoretic operators.
Approach: They propose to use question answering to predict natural logic operators using generalization capabilities of instruction-tuned language models.
Outcome: The proposed approach outperforms the best baseline on a Danish verification dataset by 4.3 accuracy points.
Probabilistic Graph Reasoning for Natural Proof Generation (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reasoning over formal representations do not explicitly consider inter-dependency between answers and proofs.
Approach: They propose a novel approach for joint answer prediction and proof generation using an induced graphical model.
Outcome: The proposed approach achieves 10%-30% improvement on QA accuracy in evaluations under diverse conditions.
ReasonBERT: Pre-trained to Reason with Distant Supervision (2021.emnlp-main)

Copied to clipboard

Challenge: Existing pre-training methods only harvest learning signals from local contexts of naturally occurring texts . ReasonBert provides a method for reasoning over long-range relations and multiple, possibly hybrid contexts.
Approach: They propose a method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts.
Outcome: The proposed method significantly improves sample efficiency over strong baselines.

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