Evaluating Defeasible Reasoning in LLMs with DEFREASING (2025.naacl-long)

Copied to clipboard

Challenge: Defeasible inferences are highly plausible but can be impacted by new information.
Approach: They construct a dataset to evaluate defeasible reasoning about property inheritance . they use generics to represent the inheritance rules because their semantics include exceptions .
Outcome: The proposed model performs poorly across all pattern types and achieves 0.64 F 1 . the best performing model only achieves F 1 and the model is not well tuned .

Similar Papers

Thinking Like a Skeptic: Defeasible Inference in Natural Language (2020.findings-emnlp)

Copied to clipboard

Challenge: Defeasible inference is a mode of reasoning in which an inference may be weakened or overturned in light of new evidence.
Approach: They propose a dataset for defeasible inference in natural language that includes extensions to existing inference datasets.
Outcome: Defeasible NLI extends existing datasets for defeaasibility inference in natural language . generative models can weaken or strengthen inferences up to 68% of the time, it shows .
Think about it! Improving defeasible reasoning by first modeling the question scenario. (2021.emnlp-main)

Copied to clipboard

Challenge: Existing literature suggests that a person forms a mental model of the problem scenario before answering questions.
Approach: They propose to have a model first create a graph of relevant influences and leverage that graph as an additional input when answering a defeasible query.
Outcome: The proposed model achieves state-of-the-art on three different defeasible reasoning datasets.
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.
LLM See, LLM Do: Leveraging Active Inheritance to Target Non-Differentiable Objectives (2024.emnlp-main)

Copied to clipboard

Challenge: Historically, high-quality labeled data has been costly to curate due to scarcity of available data and financial cost.
Approach: They characterize the impact of passive inheritance of model properties by studying how the source of synthetic data shapes models’ internal biases, calibration and preferences, and their generations’ textual attributes.
Outcome: The proposed model inheritance can increase lexical diversity or reduce toxicity.
What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations (2023.findings-emnlp)

Copied to clipboard

Challenge: Moral or ethical judgments rely heavily on the contexts in which they occur . a student model that produces defeasible contexts with improved validity, diversity, and defasibility is superior to intermediate student models .
Approach: a new study uses a student model to provide contextualizations that make an action morally acceptable . the model is based on a dataset of 115K defeasible moral actions rated highly by human annotators .
Outcome: The proposed model outperforms all intermediate models in a high-quality dataset . the model is based on 1.2M entries of contextualizations and rationales for 115K moral actions .
Could you give me a hint ? Generating inference graphs for defeasible reasoning (2021.findings-acl)

Copied to clipboard

Challenge: Defeasible reasoning is a mode of reasoning where conclusions can be overturned by taking into account new evidence.
Approach: They propose to automatically generate inference graphs for a defeasible inference task by transfer learning from a related NLP task.
Outcome: The proposed method generates meaningful graphs for a defeasible inference task and human accuracy improves by 20%.
There’s No Such Thing as Simple Reasoning for LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing work has focused on relatively complex “many-hop” reasoning problems.
Approach: They analyse the performance of fine-tuned LLMs on simple reasoning problems . they find the models remain highly brittle, being susceptible to seemingly innocent perturbations .
Outcome: The proposed models fail on simple reasoning problems, but are highly brittle . they are susceptible to seemingly innocent perturbations, such as adding duplicates to the set of premises and shuffling the order in which the premises are presented.
LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing work investigating the logical reasoning ability of large language models has focused only on a couple of inference rules of propositional and first-order logics.
Approach: They propose to use a natural language question-answering dataset to evaluate the logical reasoning ability of large language models.
Outcome: The proposed model performs poorly on a range of natural language questions using chain-of-thought prompting.
Are LLMs classical or nonmonotonic reasoners? Lessons from generics (2024.acl-short)

Copied to clipboard

Challenge: Recent research on nonmonotonic reasoning has provided evidence of impressive performance and flexible adaptation to machine generated or human critique.
Approach: They propose to use generics to explain why birds fly and exceptions such as penguins don't fly to maintain stable beliefs on truth conditions of generics.
Outcome: The proposed task features generics, such as ‘Birds fly’, and exceptions, ‘Penguins don’t fly’.
Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains (2025.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Models (LLMs) generate brief answers without reasoning processes and explanations.
Approach: They propose supervised fine-tuning and tree search to enhance LLMs’ reasoning capabilities on domain tasks.
Outcome: The proposed model improves on stock investment recommendation and legal reasoning QA tasks.

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