Salvato in:
Dettagli Bibliografici
Autori principali: Kadam, Maithili, Ferraro, Francis
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.01391
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908572897509376
author Kadam, Maithili
Ferraro, Francis
author_facet Kadam, Maithili
Ferraro, Francis
contents Large language models (LLMs) excel at general language tasks but often struggle with event-based questions-especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by 5% on average over text-only baselines, with gains up to 12% in zero-shot settings and 18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01391
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
Kadam, Maithili
Ferraro, Francis
Computation and Language
Large language models (LLMs) excel at general language tasks but often struggle with event-based questions-especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by 5% on average over text-only baselines, with gains up to 12% in zero-shot settings and 18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.
title TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
topic Computation and Language
url https://arxiv.org/abs/2510.01391