Paper Citation Record · LEDGER

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision

As of 19 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2603.07025.

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

pith.paper-citation-record.v1
2603.07025 v2

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:42:09.257514Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:22:00.993596Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T16:07:18.631370Z

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy0
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2d776383-6d61-4e2a-801c-b4499603ce22 · outbound

This paper cites Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:04.589553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a584b0f-fa38-4489-8c7c-ee692f3be648 · outbound

This paper cites audio tail.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision audio tail

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:04.661254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44961a6c-26e1-42b0-8ec9-5c0f29d1ca5c · outbound

This paper cites Training Data Only annotated ASR data was used during the training of the model.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Training Data Only annotated ASR data was used during the training of the model

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:04.743514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04599251-548c-4527-badc-18efa9c6f6d2 · outbound

This paper cites answer not found.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision answer not found

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:04.806582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b83f37e-d1ee-4e41-b214-b836e734295d · outbound

This paper cites an unresolved cited work.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:04.895799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b280e5b3-31b5-457f-b7a2-88144e4f0aee · outbound

This paper cites an unresolved cited work.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:04.986371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c83efec9-dcd4-4b1c-8641-cc413fdf9725 · outbound

This paper cites an unresolved cited work.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.083671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f29f94d-4d09-47e6-9346-e977d30fc379 · outbound

This paper cites Blsp-emo: Towards empathetic large speech-language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Blsp-emo: Towards empathetic large speech-language models,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.134538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8475616-154a-4090-816e-d98c27762d2e · outbound

This paper cites Benchmarking contextual and par- alinguistic reasoning in speech-llms: A case study with in-the- wild data,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Benchmarking contextual and par- alinguistic reasoning in speech-llms: A case study with in-the- wild data,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.215941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3091e165-bc04-46bf-9c86-8a104fde565c · outbound

This paper cites Generative spoken dialogue language modeling,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Generative spoken dialogue language modeling,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.313762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dec17be9-5a17-4f83-abe7-6e3b2f56bacb · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.405658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d61a9ffa-f886-4aae-81d8-8c2e9a2a68f3 · outbound

This paper cites Qwen2-Audio Technical Report.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Qwen2-Audio Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.496963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 877b64c4-6e9c-4747-90f3-d15e321741bb · outbound

This paper cites Salmonn: Towards generic hearing abilities for large language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Salmonn: Towards generic hearing abilities for large language models,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.586914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c36c31-bada-40d1-9d98-95502e8724b7 · outbound

This paper cites Salm: Speech- augmented language model with in-context learning for speech recognition and translation,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Salm: Speech- augmented language model with in-context learning for speech recognition and translation,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.651920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f080d2c4-ffa0-4b34-8440-403ed56c69e2 · outbound

This paper cites Meralion-audiollm: Advancing speech and language understanding for singapore,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Meralion-audiollm: Advancing speech and language understanding for singapore,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.744796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec23560-1212-45bc-bf10-7dc7578092fe · outbound

This paper cites Seallms-audio: Large audio- language models for southeast asia,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Seallms-audio: Large audio- language models for southeast asia,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.811297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 941f052b-a146-45b8-b2c5-7596fdacdd7f · outbound

This paper cites LLaMA-Omni: Seamless Speech Interaction with Large Language Models.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.886184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 891af285-33fc-45db-ae78-5ce85ee7e630 · outbound

This paper cites Analyzing mitigation strategies for catastrophic forgetting in end-to-end training of spoken language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Analyzing mitigation strategies for catastrophic forgetting in end-to-end training of spoken language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:05.949544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9910c52-fc4a-4ff8-b991-e31a3cc73d0c · outbound

This paper cites Dis- tilling an end-to-end voice assistant without instruction training data,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Dis- tilling an end-to-end voice assistant without instruction training data,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:06.015597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1c325b2-2d33-42b3-a3f0-2ffb39d09048 · outbound

This paper cites Tango 2: Aligning diffusion-based text- to-audio generations through direct preference optimization,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Tango 2: Aligning diffusion-based text- to-audio generations through direct preference optimization,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:06.212757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b3195cb-383a-4324-88da-30c2b9442ba6 · outbound

This paper cites Instruction data generation and unsupervised adap- tation for speech language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Instruction data generation and unsupervised adap- tation for speech language models,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:06.390935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation effcaceb-e8ec-45c6-bcc9-e245ad1357c5 · outbound

This paper cites Speechless: Speech Instruction Training Without Speech for Low Resource Languages,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Speechless: Speech Instruction Training Without Speech for Low Resource Languages,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:06.582277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29adec66-3801-409b-ae2b-d5541b2a59f6 · outbound

This paper cites BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:06.739946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff80b5db-251e-4481-a1c2-c17a27b628c2 · outbound

This paper cites Inte- grating speech self-supervised learning models and large language models for asr,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Inte- grating speech self-supervised learning models and large language models for asr,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:06.901189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e6cc7a6-7984-411c-8c96-0aa38fa6115e · outbound

This paper cites An end-to-end speech summarization using large lan- guage model,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision An end-to-end speech summarization using large lan- guage model,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:07.105859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e873a736-7b59-4a06-9ac7-8631300c3c16 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:07.244639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d71c9ade-929a-41a9-88f1-011f16bc14ac · outbound

This paper cites Robust speech recognition via large-scale weak su- pervision,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Robust speech recognition via large-scale weak su- pervision,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:07.426368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7915a65-e7cc-4d66-a58b-b2f7dfe49549 · outbound

This paper cites A two-stage lora strategy for expanding language capabilities in multilingual asr models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision A two-stage lora strategy for expanding language capabilities in multilingual asr models,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:07.648311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58b8e062-eda9-4b4a-a554-ea6da2e90c30 · outbound

This paper cites Language-routing mixture of experts for multilingual and code-switching speech recognition,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Language-routing mixture of experts for multilingual and code-switching speech recognition,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:07.828697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d1ae25-085d-4f4f-a907-118ed0d78ae2 · outbound

This paper cites Adap- tive gating in mixture-of-experts based language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Adap- tive gating in mixture-of-experts based language models,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:07.995689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e2c0d8-398b-4d26-b064-a8ebd9abb304 · outbound

This paper cites Sea-lion: Southeast asian languages in one network,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Sea-lion: Southeast asian languages in one network,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.151807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28299d65-a305-4da1-8af6-0c47b52e6c8b · outbound

This paper cites The Llama 3 Herd of Models.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision The Llama 3 Herd of Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.276139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a16de5-4d96-4d9e-8bdb-cbe3d20fcd95 · outbound

This paper cites Common voice: A massively-multilingual speech corpus,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Common voice: A massively-multilingual speech corpus,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.383015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 606e5f28-0483-461a-b7d7-61d18c51d90a · outbound

This paper cites viV oice: Enabling vietnamese multi-speaker speech synthesis,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision viV oice: Enabling vietnamese multi-speaker speech synthesis,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.495564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a37499-afbb-4332-bff3-350dde3dfdb2 · outbound

This paper cites Yodas: Youtube-oriented dataset for audio and speech,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Yodas: Youtube-oriented dataset for audio and speech,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.586485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d785b59c-9350-489e-b2c6-4b43dfbe66a7 · outbound

This paper cites Magic data open source cor- pus (id: 101),.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision Magic data open source cor- pus (id: 101),

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.671725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08956cfe-86b7-46c2-a69f-c5aacab12e00 · outbound

This paper cites URO-bench: Towards comprehensive eval- uation for end-to-end spoken dialogue models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision URO-bench: Towards comprehensive eval- uation for end-to-end spoken dialogue models,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.761675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6ab5e8-660d-4a5f-8848-bbcfebd5ab43 · outbound

This paper cites VoiceBench: Benchmarking LLM-Based Voice Assistants.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision VoiceBench: Benchmarking LLM-Based Voice Assistants

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.853789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5c89243-3be3-48c1-b189-ae7a610c04f0 · outbound

This paper cites AudioBench: A universal benchmark for audio large language models,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision AudioBench: A universal benchmark for audio large language models,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:08.996908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf193e24-438a-425f-93ac-cb718708a220 · outbound

This paper cites MLQA: Evaluating Cross-lingual Extractive Question Answering.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision MLQA: Evaluating Cross-lingual Extractive Question Answering

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:09.093355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d15af879-e5e4-4909-ab46-cdb6525757da · outbound

This paper cites PEDANTS: Cheap but effective and interpretable answer equiv- alence,.

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision PEDANTS: Cheap but effective and interpretable answer equiv- alence,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:09.197246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24d8b381-7d8d-4761-8d9d-7a3e93f2bca4 · outbound

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

Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T18:42:09.257514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2d776383-6d61-4e2a-801c-b4499603ce22 · inbound