| 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 . |
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. |
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. |
Multilingual Reasoning via Self-training (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have introduced eclectic strategies to improve reasoning beyond English, but these methods are related to specific language that is not always optimal for reasoning. |
| Approach: | They propose a modular approach that instructs models to structure reasoning passages in a different problem space and then self-refines their capabilities to deliver step-wise reasoning passage. |
| Outcome: | The proposed approach achieves significant improvements in multilingual reasoning of various models and task, with improved reasoning consistency across languages. |
Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods that decompose multi-hop questions into single hop sub-questions are difficult to implement. |
| Approach: | They propose to use random-walks to guide pre-trained language models to map multi-hop questions to random-walked paths that lead to the answer. |
| Outcome: | The proposed methods improve on two T5 LMs. |
Can Language Models Learn Embeddings of Propositional Logic Assertions? (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for automating reasoning can no longer be used for natural language tasks. |
| Approach: | They propose to use transformer-based language models to reason about knowledge expressed in natural language rather than using LMs to perform reasoning directly. |
| Outcome: | The proposed approach is feasible to some extent, but lacks robustness. |
Towards Reasoning in Large Language Models: A Survey (2023.findings-acl)
Copied to clipboard
| Challenge: | Reasoning is a fundamental aspect of human intelligence that plays a crucial role in many intellectual activities. |
| Approach: | They propose to improve LLMs' ability to elicit reasoning by providing exemplars or prompts to model reasoning. |
| Outcome: | This paper provides a comprehensive overview of the state of knowledge on reasoning in large language models. |
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (P19-1)
Copied to clipboard
| 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. |
Current Advances in LLM Reasoning (2026.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial examines comprehensive evaluation strategies to assess the reasoning abilities of large language models (LLMs) advanced inference time methods and post-training methods that aim to make LLMs think more like humans are discussed in this tutorial. |
| Approach: | This tutorial explores comprehensive evaluation strategies to assess the reasoning abilities of large language models (LLMs) and discusses two types of methods to improve models’ reasoning: advanced inference time methods, structured and self-improvement inference methods, and post-training methods, such as RLHF, DPO, and GRPO. |
| Outcome: | This tutorial examines evaluation strategies to assess the reasoning abilities of large language models and discusses two types of methods to improve models’ reasoning. |
Recent Advances in Pre-trained Language Models: Why Do They Work and How Do They Work (2022.aacl-tutorials)
Copied to clipboard
| Challenge: | Pre-trained language models are language models that are pre-taught on large-scaled corpora in a self-supervised fashion. |
| Approach: | This tutorial provides a broad and comprehensive introduction to pre-trained language models . it focuses on emerging methods that enable PLMs to perform diverse downstream tasks . |
| Outcome: | This tutorial focuses on the benefits of pre-trained language models and how to use them in NLP tasks. |
Scalable Construction and Reasoning of Massive Knowledge Bases (N18-6)
Copied to clipboard
| Challenge: | Existing knowledge mining systems assume abundant human annotations for training high quality machine learning models, which is impractical when trying to deploy IE systems to a broad range of domains, settings and languages. |
| Approach: | They introduce how to extract structured facts from text corpora to construct knowledge bases. |
| Outcome: | The proposed methods are weakly-supervised and domain-independent for knowledge base construction across various domains. |