Paper Citation Record · LEDGER

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages

As of 3 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2509.14804.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.14804 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T16:27:37.596817Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T16:27:37.596817Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-05-18T16:31:37.277945Z

Reference resolution

32 of 32 outbound references displayed

verified exact19
verified fuzzy7
unresolved4
parse uncertain1
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 37cf92eb-eb84-4c8b-ac53-9d05791273a2 · outbound

This paper cites Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T16:31:37.281235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation bfa93736-5e24-489a-995b-03f2ff9374e5 · outbound

This paper cites To extract rich speech represen- tations and support multitask requirements, we continue pretraining a multilingual SSL XLSR model on readily available unlabeled speech.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages To extract rich speech represen- tations and support multitask requirements, we continue pretraining a multilingual SSL XLSR model on readily available unlabeled speech

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.408474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 19ed7666-5217-48af-ab88-42d2532c3999 · outbound

This paper cites an unresolved cited work.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-18T16:32:45.405067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0cff94d7-9c47-4722-9d31-d29c68715277 · outbound

This paper cites an unresolved cited work.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-05-18T16:32:45.428470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation bcec76a0-f450-415f-919c-46f0763de14b · outbound

This paper cites an unresolved cited work.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Unresolved cited work

Reference 5

Resolution: parse uncertain; raw_fallback, observed 2026-05-18T16:32:45.425268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation bbbb7a75-f959-41cb-8c6a-05d811f124a7 · outbound

This paper cites Giga2 Test.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Giga2 Test

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.415360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1a3d152f-fd09-4d29-8ce9-cce669c3bb24 · outbound

This paper cites an unresolved cited work.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-18T16:32:45.418578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8fcd6653-12f5-4b5e-ad96-2f5ab9e09edd · outbound

This paper cites an unresolved cited work.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-05-18T16:32:45.421882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 2d685b73-3a01-4bf0-a409-2f3b50eaefe9 · outbound

This paper cites GPT-4 Technical Report.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages GPT-4 Technical Report

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:31:37.200214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7050ce9a-e043-498f-9814-55fe49077028 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:31:37.274058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ff55fc10-145d-47d9-a655-bc7e609b9c62 · outbound

This paper cites Qwen2 Technical Report.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Qwen2 Technical Report

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:31:37.246569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8a7931aa-9b85-4f9f-9d7c-490653cc6fb0 · outbound

This paper cites Qwen2-Audio Technical Report.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Qwen2-Audio Technical Report

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:31:37.214337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 92edd316-7874-46cc-83ef-472a92329881 · outbound

This paper cites Kimi-Audio Technical Report.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Kimi-Audio Technical Report

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:31:37.267356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6926b130-d033-4f16-badd-5e1c9729d192 · outbound

This paper cites Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.190198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7287100f-cfe4-4531-b7de-b1e9b85c8023 · outbound

This paper cites Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.195229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1cd5ced8-1692-4beb-8b08-f654536cbb5a · outbound

This paper cites Voxtral.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Voxtral

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.256969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5e0eb325-70d6-4597-a064-93b3bef5b1ae · outbound

This paper cites Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.222863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b720b867-8b51-4b57-821a-a6cd1d1ae847 · outbound

This paper cites GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:31:37.251470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 050ac82d-14d1-4658-bac8-7b4904c2fa6e · outbound

This paper cites Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.205947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8894e950-3020-49ca-9575-86dddec8e89a · outbound

This paper cites TASTE: Text-Aligned Speech To- kenization and Embedding for Spoken Language Modeling.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages TASTE: Text-Aligned Speech To- kenization and Embedding for Spoken Language Modeling

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.185120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8e507a9a-fb18-426f-9b01-fd7b5e506ef5 · outbound

This paper cites SALMONN: Towards Generic Hearing Abilities for Large Language Mod- els.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages SALMONN: Towards Generic Hearing Abilities for Large Language Mod- els

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.435859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 652210ae-bf64-44aa-bd94-05f4a537f8c0 · outbound

This paper cites Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.443475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f38737e3-6cba-4b9d-9031-e492d7d10278 · outbound

This paper cites Efficient Scaling for LLM-based ASR.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Efficient Scaling for LLM-based ASR

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.237746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6e688816-347c-4852-acfd-4dbdb1df2628 · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Robust Speech Recognition via Large-Scale Weak Supervision

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.412046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8343647e-129e-4658-bc6f-18c912e44ef8 · outbound

This paper cites Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.218556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 93284ac9-394a-42dc-9ced-1d4b75bc47dd · outbound

This paper cites OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.228057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 62c6e0bb-dc4c-4088-b0a4-cdbda7289aea · outbound

This paper cites XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.439676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4f7c7ab8-2a3a-4871-a4d9-7787a078a5cd · outbound

This paper cites Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.210307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a8438032-1c43-4fd7-a270-741ef50b734a · outbound

This paper cites XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.262268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 15254c82-8fde-4ccc-a224-12a3523f118c · outbound

This paper cites GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.242377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d2c80595-9118-415f-b188-53d905fc1546 · outbound

This paper cites MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:31:37.233096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f2a148e1-c25a-4a04-91fe-f50ffc527646 · outbound

This paper cites Common V oice: A Massively-Multilingual Speech Corpus.

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages Common V oice: A Massively-Multilingual Speech Corpus

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T16:32:45.432084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

Observation 37cf92eb-eb84-4c8b-ac53-9d05791273a2 · inbound