MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing
We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into {entailment, contradiction, neutral}, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMORPHNatural Language InferenceSimilar Papers 제목 키워드 기반
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
Stepwise inference protocols, such as scratchpads and chain-of-thought, help language models solve complex problems by decomposing them into a sequence of simpler subproblems. Despite the significant gain in performance …
DiversityRethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective
Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Stepwise model routing mitigates this issue by dynamically assigning re…
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Traditional inference time scaling methods ut…
Decision MakingQLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides va…
PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints
Large Language Models (LLMs) often exhibit limited logical coherence, mapping premises to conclusions without adherence to explicit inference rules. We propose Proof-Carrying Reasoning with LLMs (PCRLLM), a framework tha…