Copertina

Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cooray, Lakshan, Sumanathilaka, Deshan, Raju, Pattigadapa Venkatesh
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance
di: Perera, Peshala, et al.
Pubblicazione: (2025)

A Survey on Lexical Ambiguity Detection and Word Sense Disambiguation
di: Abeysiriwardana, Miuru, et al.
Pubblicazione: (2024)

Bridging Lexical Ambiguity and Vision: A Mini Review on Visual Word Sense Disambiguation
di: Nilukshi, Shashini, et al.
Pubblicazione: (2026)

EmoScan: Automatic Screening of Depression Symptoms in Romanized Sinhala Tweets
di: Hewapathirana, Jayathi, et al.
Pubblicazione: (2024)

Swa Bhasha: Message-Based Singlish to Sinhala Transliteration
di: Athukorala, Maneesha U., et al.
Pubblicazione: (2024)

Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
di: Sumanathilaka, Deshan, et al.
Pubblicazione: (2025)

An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
di: Sumanathilaka, Deshan, et al.
Pubblicazione: (2026)

SwanNLP at SemEval-2026 Task 5: An LLM-based Framework for Plausibility Scoring in Narrative Word Sense Disambiguation
di: Sumanathilaka, Deshan, et al.
Pubblicazione: (2026)

Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation
di: Sumanathilaka, T. G. D. K., et al.
Pubblicazione: (2024)

IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages
di: Sumanathilaka, Deshan, et al.
Pubblicazione: (2025)

Hybrid Emotion Recognition: Enhancing Customer Interactions Through Acoustic and Textual Analysis
di: Wewelwala, Sahan Hewage, et al.
Pubblicazione: (2025)

A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior
di: Jayasuriya, Nikil, et al.
Pubblicazione: (2025)

Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approach
di: Mohammadi, Amir Hossein, et al.
Pubblicazione: (2026)

The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA
di: Zarrinkia, Yasaman, et al.
Pubblicazione: (2026)

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data
di: Lu, Yuxuan, et al.
Pubblicazione: (2025)

QA-prompting: Improving Summarization with Large Language Models using Question-Answering
di: Sinha, Neelabh
Pubblicazione: (2025)

Multi-Dimensional Evaluation of Text Summarization with In-Context Learning
di: Jain, Sameer, et al.
Pubblicazione: (2023)

On Context Utilization in Summarization with Large Language Models
di: Ravaut, Mathieu, et al.
Pubblicazione: (2023)

Evaluating Temporal Consistency in Multi-Turn Language Models
di: Atri, Yash Kumar, et al.
Pubblicazione: (2026)

Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
di: Wang, Jinhan, et al.
Pubblicazione: (2024)

Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation
di: Huang, Wenyu, et al.
Pubblicazione: (2025)

Error-Aware Knowledge Distillation via Targeted Revision for Customer-Service Summarization
di: Lee, Hee-Jin, et al.
Pubblicazione: (2025)

Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance
di: Xu, Borui, et al.
Pubblicazione: (2025)

ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering
di: Molfese, Francesco Maria, et al.
Pubblicazione: (2025)

ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models
di: Yan, Jianxin, et al.
Pubblicazione: (2025)

TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models
di: Zhang, Yiran, et al.
Pubblicazione: (2025)

Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation
di: Subramanian, Seganrasan, et al.
Pubblicazione: (2025)

Syn-QA2: Evaluating False Assumptions in Long-tail Questions with Synthetic QA Datasets
di: Daswani, Ashwin, et al.
Pubblicazione: (2024)

Evaluating Language Models as Synthetic Data Generators
di: Kim, Seungone, et al.
Pubblicazione: (2024)

SWE-QA: Can Language Models Answer Repository-level Code Questions?
di: Peng, Weihan, et al.
Pubblicazione: (2025)

Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data
di: Chen, Yuhao, et al.
Pubblicazione: (2024)

Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA
di: Su, Jinyan, et al.
Pubblicazione: (2026)

Comparative Personalization for Multi-document Summarization
di: Li, Haoyuan, et al.
Pubblicazione: (2025)

Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Models
di: Hong, Mengze, et al.
Pubblicazione: (2024)

Can we Evaluate RAGs with Synthetic Data?
di: van Elburg, Jonas, et al.
Pubblicazione: (2025)

Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources
di: Sumanathilaka, Deshan, et al.
Pubblicazione: (2025)

Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA
di: Tang, Xing, et al.
Pubblicazione: (2026)

Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations
di: Liu, Yu Lu, et al.
Pubblicazione: (2026)

BookAsSumQA: An Evaluation Framework for Aspect-Based Book Summarization via Question Answering
di: Miyazato, Ryuhei, et al.
Pubblicazione: (2025)

TrueBrief: Faithful Summarization through Small Language Models
di: Lakara, Kumud, et al.
Pubblicazione: (2025)