Exploring the Influence of Relevant Knowledge for Natural Language Generation Interpretability

• URL: http://arxiv.org/abs/2510.24179v1
• Date: Tue, 28 Oct 2025 08:34:01 GMT
• Title: Exploring the Influence of Relevant Knowledge for Natural Language Generation Interpretability
• Abstract summary: This paper explores the influence of external knowledge integration in Natural Language Generation (NLG)<n>We extend the CommonGen dataset by creating KITGI, a benchmark that pairs input concept sets with retrieved semantic relations from ConceptNet.<n>Using the T5-Large model, we compare sentence generation under two conditions: with full external knowledge and with filtered knowledge.
• Score: 0.13764085113103217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper explores the influence of external knowledge integration in Natural Language Generation (NLG), focusing on a commonsense generation task. We extend the CommonGen dataset by creating KITGI, a benchmark that pairs input concept sets with retrieved semantic relations from ConceptNet and includes manually annotated outputs. Using the T5-Large model, we compare sentence generation under two conditions: with full external knowledge and with filtered knowledge where highly relevant relations were deliberately removed. Our interpretability benchmark follows a three-stage method: (1) identifying and removing key knowledge, (2) regenerating sentences, and (3) manually assessing outputs for commonsense plausibility and concept coverage. Results show that sentences generated with full knowledge achieved 91\% correctness across both criteria, while filtering reduced performance drastically to 6\%. These findings demonstrate that relevant external knowledge is critical for maintaining both coherence and concept coverage in NLG. This work highlights the importance of designing interpretable, knowledge-enhanced NLG systems and calls for evaluation frameworks that capture the underlying reasoning beyond surface-level metrics.

Related papers

• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach [33.17711262799183]
  We develop a task-agnostic structured knowledge hunter for knowledge-enhanced text generation tasks.<n>Our model achieves high interpretability, enabling users to comprehend the model output generation process.<n>We empirically demonstrate the effectiveness of our model in both internal knowledge-enhanced table-to-text generation on the RotoWireFG dataset and external knowledge-enhanced dialogue response generation on the KdConv dataset.
  arXiv  Detail & Related papers  (2025-11-28T16:43:46Z)
• Filling the Gap: Is Commonsense Knowledge Generation useful for Natural Language Inference? [0.0]
  Natural Language Inference (NLI) is the task of determining the semantic entailment of a premise for a given hypothesis.<n>Existing commonsense resources lack sufficient coverage for a variety of premise-hypothesis pairs.<n>This study explores the potential of Large Language Models as commonsense knowledge generators for NLI along two key dimensions.
  arXiv  Detail & Related papers  (2025-07-20T19:42:45Z)
• Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering [9.814926166669366]
  We propose Know3-RAG, a knowledge-aware RAG framework that leverages structured knowledge from knowledge graphs (KGs) to guide three core stages of the RAG process, including retrieval, generation, and filtering.<n> Experiments on multiple open-domain QA benchmarks demonstrate that Know3-RAG consistently outperforms strong baselines, significantly reducing hallucinations and enhancing answer reliability.
  arXiv  Detail & Related papers  (2025-05-19T03:25:18Z)
• Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation [25.54961029763311]
  Context-Prior Augmented Citation Generation task requires models to generate citations considering both external and internal knowledge.<n>We introduce RAEL, the paradigm for our task, and also design INTRALIGN, an integrated method containing customary data generation and an alignment algorithm.<n>Our extended experiments further reveal that retrieval quality, question types, and model knowledge have considerable influence on the trustworthiness in citation generation.
  arXiv  Detail & Related papers  (2025-04-21T04:50:16Z)
• ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation [91.20492150248106]
  We investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases.<n>We propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs.<n> Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory.
  arXiv  Detail & Related papers  (2025-02-21T15:50:41Z)
• S$^2$DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion [19.09682423796942]
  We propose a Semantic Structure-aware Denoising Network (S$2$DN) for inductive Knowledge Graph Completion.<n>Our goal is to learn adaptable general semantics and reliable structures to distill consistent semantic knowledge.<n>Experiments conducted on three benchmark KGs demonstrate that S$2$DN surpasses the performance of state-of-the-art models.
  arXiv  Detail & Related papers  (2024-12-20T12:03:33Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• IXA/Cogcomp at SemEval-2023 Task 2: Context-enriched Multilingual Named Entity Recognition using Knowledge Bases [53.054598423181844]
  We present a novel NER cascade approach comprising three steps. We empirically demonstrate the significance of external knowledge bases in accurately classifying fine-grained and emerging entities. Our system exhibits robust performance in the MultiCoNER2 shared task, even in the low-resource language setting.
  arXiv  Detail & Related papers  (2023-04-20T20:30:34Z)
• Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis [96.53859361560505]
  We propose a knowledge graph augmented network (KGAN) to incorporate external knowledge with explicitly syntactic and contextual information. KGAN captures the sentiment feature representations from multiple perspectives, i.e., context-, syntax- and knowledge-based. Experiments on three popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN.
  arXiv  Detail & Related papers  (2022-01-13T08:25:53Z)
• Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers [54.417299589288184]
  We investigate models for complementing the distributional knowledge of BERT with conceptual knowledge from ConceptNet and its corresponding Open Mind Common Sense (OMCS) corpus. Our adapter-based models substantially outperform BERT on inference tasks that require the type of conceptual knowledge explicitly present in ConceptNet and OMCS.
  arXiv  Detail & Related papers  (2020-05-24T15:49:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.