Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Can Large Language Models Understand, Reason About, and Generate Code-Switched Text? (2026)
OLA: Output Language Alignment in Code-Switched LLM Interactions (2026)
Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization (2025)
Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models (2026)
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues (2026)
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (2026)
SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generation (2025)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2026-01-28T01:39:06.307Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":317,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6924998760223389},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"69797bd973586b8d6cefad8b","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false},"createdAt":"2026-01-28T03:00:41.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"arXivlens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/pingpong-a-natural-benchmark-for-multi-turn-code-switching-dialogues-324-176b18f2\n- Executive Summary\n- Detailed Breakdown\n- Practical Applications","html":"

arXivlens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/pingpong-a-natural-benchmark-for-multi-turn-code-switching-dialogues-324-176b18f2

Executive Summary
Detailed Breakdown
Practical Applications

\n","updatedAt":"2026-01-28T03:00:41.077Z","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6542751789093018},"editors":["avahal"],"editorAvatarUrls":["/avatars/743a009681d5d554c27e04300db9f267.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2601.17277","authors":[{"_id":"6978819c026bdf047311700e","user":{"_id":"65af40481216d503271e7d95","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65af40481216d503271e7d95/7BvAFiSHbL4rShMzdsLyd.png","isPro":false,"fullname":"Mohammad Rifqi Farhansyah","user":"rifqifarhansyah","type":"user"},"name":"Mohammad Rifqi Farhansyah","status":"claimed_verified","statusLastChangedAt":"2026-01-27T09:42:31.957Z","hidden":false},{"_id":"6978819c026bdf047311700f","user":{"_id":"64e44caa3ad886e1af2768f5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64e44caa3ad886e1af2768f5/PUjbVLCspXNvzRMfmyZXR.jpeg","isPro":false,"fullname":"Hanif Muhammad Zhafran","user":"hanifmz0711","type":"user"},"name":"Hanif Muhammad Zhafran","status":"admin_assigned","statusLastChangedAt":"2026-01-27T14:39:29.608Z","hidden":false},{"_id":"6978819c026bdf0473117010","user":{"_id":"60c7fe961ef9b0a2ad1d398e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c7fe961ef9b0a2ad1d398e/S4ewjcFp_q0Fj6QK8GwtL.jpeg","isPro":false,"fullname":"Farid Adilazuarda","user":"faridlazuarda","type":"user"},"name":"Farid Adilazuarda","status":"admin_assigned","statusLastChangedAt":"2026-01-27T14:39:35.653Z","hidden":false},{"_id":"6978819c026bdf0473117011","name":"Shamsuddeen Hassan Muhammad","hidden":false},{"_id":"6978819c026bdf0473117012","name":"Maryam Ibrahim Mukhtar","hidden":false},{"_id":"6978819c026bdf0473117013","name":"Nedjma Ousidhoum","hidden":false},{"_id":"6978819c026bdf0473117014","user":{"_id":"5f5c4b20e56d546cd6233098","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1637813888895-5f5c4b20e56d546cd6233098.jpeg","isPro":false,"fullname":"Genta Indra Winata","user":"gentaiscool","type":"user"},"name":"Genta Indra Winata","status":"admin_assigned","statusLastChangedAt":"2026-01-27T14:39:54.342Z","hidden":false},{"_id":"6978819c026bdf0473117015","name":"Ayu Purwarianti","hidden":false},{"_id":"6978819c026bdf0473117016","user":{"_id":"61a4dc053205e107691e0d82","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61a4dc053205e107691e0d82/BESoEHlHYXstXudh6dOdT.jpeg","isPro":true,"fullname":"Alham Fikri Aji","user":"afaji","type":"user"},"name":"Alham Fikri Aji","status":"admin_assigned","statusLastChangedAt":"2026-01-27T14:40:03.188Z","hidden":false}],"publishedAt":"2026-01-24T03:31:08.000Z","submittedOnDailyAt":"2026-01-27T06:46:04.281Z","title":"PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues","submittedOnDailyBy":{"_id":"65af40481216d503271e7d95","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65af40481216d503271e7d95/7BvAFiSHbL4rShMzdsLyd.png","isPro":false,"fullname":"Mohammad Rifqi Farhansyah","user":"rifqifarhansyah","type":"user"},"summary":"Code-switching is a widespread practice among the world's multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PingPong, a benchmark for natural multi-party code-switching dialogues covering five language-combination variations, some of which are trilingual. Our dataset consists of human-authored conversations among 2 to 4 participants covering authentic, multi-threaded structures where replies frequently reference much earlier points in the dialogue. We demonstrate that our data is significantly more natural and structurally diverse than machine-generated alternatives, offering greater variation in message length, speaker dominance, and reply distance. Based on these dialogues, we define three downstream tasks: Question Answering, Dialogue Summarization, and Topic Classification. Evaluations of several state-of-the-art language models on PingPong reveal that performance remains limited on code-switched inputs, underscoring the urgent need for more robust NLP systems capable of addressing the intricacies of real-world multilingual discourse.","upvotes":6,"discussionId":"6978819c026bdf0473117017","ai_summary":"Code-switching presents complex challenges in multilingual communication that current language models struggle to address effectively.","ai_keywords":["code-switching","multilingual discourse","natural language processing","language models","dialogue understanding"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65af40481216d503271e7d95","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65af40481216d503271e7d95/7BvAFiSHbL4rShMzdsLyd.png","isPro":false,"fullname":"Mohammad Rifqi Farhansyah","user":"rifqifarhansyah","type":"user"},{"_id":"60c7fe961ef9b0a2ad1d398e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c7fe961ef9b0a2ad1d398e/S4ewjcFp_q0Fj6QK8GwtL.jpeg","isPro":false,"fullname":"Farid Adilazuarda","user":"faridlazuarda","type":"user"},{"_id":"64e44caa3ad886e1af2768f5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64e44caa3ad886e1af2768f5/PUjbVLCspXNvzRMfmyZXR.jpeg","isPro":false,"fullname":"Hanif Muhammad Zhafran","user":"hanifmz0711","type":"user"},{"_id":"66fe1d65d74232f132b0eab8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66fe1d65d74232f132b0eab8/yCLrokh_e-vpuFNezHwxl.png","isPro":false,"fullname":"Akmal Mahardika Nurwahyu Pratama","user":"akmaldika","type":"user"},{"_id":"67f785e45a7c6fd22419e870","avatarUrl":"/avatars/7cd6346c183e9e500c56418719fc9ebc.svg","isPro":false,"fullname":"Raden Rafly Hanggaraksa Budiarto","user":"raflyhangga","type":"user"},{"_id":"67194b52bf6d5eae280b5d88","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/S-t_bm6HuGz2CLRL3va-F.png","isPro":false,"fullname":"Osama","user":"OsamaO","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2601.17277

PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues

Published on Jan 24

· Submitted by

Mohammad Rifqi Farhansyah on Jan 27

Upvote

Authors:

Mohammad Rifqi Farhansyah ,

Hanif Muhammad Zhafran ,

Farid Adilazuarda ,

Genta Indra Winata ,

Alham Fikri Aji

Abstract

Code-switching presents complex challenges in multilingual communication that current language models struggle to address effectively.

AI-generated summary

Code-switching is a widespread practice among the world's multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PingPong, a benchmark for natural multi-party code-switching dialogues covering five language-combination variations, some of which are trilingual. Our dataset consists of human-authored conversations among 2 to 4 participants covering authentic, multi-threaded structures where replies frequently reference much earlier points in the dialogue. We demonstrate that our data is significantly more natural and structurally diverse than machine-generated alternatives, offering greater variation in message length, speaker dominance, and reply distance. Based on these dialogues, we define three downstream tasks: Question Answering, Dialogue Summarization, and Topic Classification. Evaluations of several state-of-the-art language models on PingPong reveal that performance remains limited on code-switched inputs, underscoring the urgent need for more robust NLP systems capable of addressing the intricacies of real-world multilingual discourse.

View arXiv page View PDF Add to collection