Paper Citation Record · LEDGER

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

As of 12 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 5 inbound Pith citation observations for arXiv:2505.17496.

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

pith.paper-citation-record.v1
2505.17496 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:49:32.643541Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:49:27.503557Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T00:14:04.018407Z

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy24
unresolved22
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 118b8495-b3c1-4f18-bd1f-c222269dc67c · outbound

This paper cites Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:27.503557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae861de5-1056-44e4-b436-7cd7074e9a60 · outbound

This paper cites an unresolved cited work.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:49:37.739818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3a4a6fe1-047a-490c-9b91-f6b26c8daab2 · outbound

This paper cites model merging after experience replay.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models model merging after experience replay

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:49:37.616001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3dfc9cbe-9d1e-4b87-a101-f2505f0c55f7 · outbound

This paper cites Catastrophic forgetting Fig.3 shows the evaluation results on instruction-following and question answering in each training stage on T2T setting.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Catastrophic forgetting Fig.3 shows the evaluation results on instruction-following and question answering in each training stage on T2T setting

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:37.430359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 06ceb650-210d-490b-8cc9-dec78f6770b1 · outbound

This paper cites The results demonstrate that expe- rience replay is the most effective method, with further perfor- mance gains achievable by combining it with other techniques.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models The results demonstrate that expe- rience replay is the most effective method, with further perfor- mance gains achievable by combining it with other techniques

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:37.269287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3797e6e1-9d33-4a8e-9552-408c0b578a29 · outbound

This paper cites GPT-4 Technical Report.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models GPT-4 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:27.974838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0baea6ba-f3f0-4bd4-be3e-eae0565a93b6 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:28.073588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc749462-ff52-481e-a87a-7a3623d4b8bb · outbound

This paper cites The Llama 3 Herd of Models.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:28.203129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a31ed582-f950-460f-9364-343267f7fd3c · outbound

This paper cites Qwen2.5 Technical Report.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Qwen2.5 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:28.267095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 419642c6-4c42-42d6-89a6-d65afa5ac256 · outbound

This paper cites On generative spoken language modeling from raw audio,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models On generative spoken language modeling from raw audio,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:37.124544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0c42895f-bbe2-4f2f-b426-65a259956dfc · outbound

This paper cites Neural codec language models are zero-shot text to speech synthesizers,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Neural codec language models are zero-shot text to speech synthesizers,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:36.990638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f9c63014-3cb0-48d8-8af5-6f85d8fdbb59 · outbound

This paper cites Seamless: Multilingual Expressive and Streaming Speech Translation.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Seamless: Multilingual Expressive and Streaming Speech Translation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:28.537697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e3323cd-c372-4bd9-8862-80d0d81e1159 · outbound

This paper cites Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:28.620577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0569789-654b-4876-974a-748e520e66aa · outbound

This paper cites Dynamic-superb: Towards a dynamic, col- laborative, and comprehensive instruction-tuning benchmark for speech,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Dynamic-superb: Towards a dynamic, col- laborative, and comprehensive instruction-tuning benchmark for speech,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:36.817565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f138d9a8-3898-4499-998b-906c899ce561 · outbound

This paper cites On The Landscape of Spoken Language Models: A Comprehensive Survey.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models On The Landscape of Spoken Language Models: A Comprehensive Survey

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:28.778868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4e7bcb-fd9c-4989-96f3-539928d79ccd · outbound

This paper cites UniverSLU: Universal spoken language under- standing for diverse tasks with natural language instructions,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models UniverSLU: Universal spoken language under- standing for diverse tasks with natural language instructions,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:36.618209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 30d8664d-fa11-4dfb-9095-ce0d551ce349 · outbound

This paper cites ESPnet-SpeechLM: An open speech language model toolkit,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models ESPnet-SpeechLM: An open speech language model toolkit,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:36.428957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9848b011-631c-4159-a246-b1354fd81a78 · outbound

This paper cites Joint audio and speech understanding,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Joint audio and speech understanding,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:36.222228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 620f5420-a1b9-4267-99c9-541345a9fe36 · outbound

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

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models SALMONN: Towards generic hearing abilities for large language models,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:36.005034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dbbceda6-52d2-4195-9d57-3d7cc9659bc2 · outbound

This paper cites Desta: Enhancing speech language models through descriptive speech-text alignment,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Desta: Enhancing speech language models through descriptive speech-text alignment,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.806551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0279a263-cbd1-4f53-baf0-7984b7ea1c83 · outbound

This paper cites DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:29.352657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2f4d02f-e771-47cd-b34c-1624906e9d27 · outbound

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

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:29.431423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64118d62-9c24-4235-9d94-d07d1e2d7cf8 · outbound

This paper cites Qwen2-Audio Technical Report.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Qwen2-Audio Technical Report

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:29.530299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb46d111-c5cb-4e3e-b5f2-c2dcd445e741 · outbound

This paper cites SpeechGPT: Empowering large language mod- els with intrinsic cross-modal conversational abilities,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models SpeechGPT: Empowering large language mod- els with intrinsic cross-modal conversational abilities,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.693307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 57cc660e-5096-4383-a1bb-daec940cb195 · outbound

This paper cites Audiolm: A language modeling approach to au- dio generation,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Audiolm: A language modeling approach to au- dio generation,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.583710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2472925a-b332-4cff-a7f4-cec303d410ee · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Moshi: a speech-text foundation model for real-time dialogue

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:29.740906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99f94a9b-b0ba-4851-9d93-67f50709eca7 · outbound

This paper cites Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:29.836731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a92c2aa1-99ea-4f6b-8ef0-909ed81a58a6 · outbound

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

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:29.942638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1767e8f5-1977-445a-90b2-13ef00464690 · outbound

This paper cites Building a Taiwanese Mandarin Spoken Language Model: A First Attempt.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Building a Taiwanese Mandarin Spoken Language Model: A First Attempt

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:30.027800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df2d0df4-04e0-46a9-90aa-89df1497546e · outbound

This paper cites An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:30.102903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 069b8776-e893-4f6b-8e5e-ae8d0aa49acd · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:30.202377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c53032a3-6cc2-4fa3-99a0-a600906fa832 · outbound

This paper cites Mitigating the alignment tax of rlhf,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Mitigating the alignment tax of rlhf,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.464670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 63455f88-dc64-46b2-ab69-adce8736061a · outbound

This paper cites Desta: Enhancing speech language models through descriptive speech-text alignment,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Desta: Enhancing speech language models through descriptive speech-text alignment,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.332950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dc8e5282-bcd7-48ca-a78c-36ad036da432 · outbound

This paper cites Experience replay for continual learning,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Experience replay for continual learning,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.198113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e906b271-637d-4304-9b4a-dd0ad6989dd3 · outbound

This paper cites Lifelong learning of large language model based agents: A roadmap,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Lifelong learning of large language model based agents: A roadmap,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:30.738275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b11aedce-d358-4e37-9248-707740270df0 · outbound

This paper cites Vqacl: A novel visual question answering con- tinual learning setting,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Vqacl: A novel visual question answering con- tinual learning setting,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:35.046797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 35cf9cd9-bf56-4c92-9735-e02834a7f671 · outbound

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

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Salmonn: Towards generic hearing abilities for large language models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:34.854269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation db61f869-be6e-4470-a759-9772d27d2f7c · outbound

This paper cites Ties-merging: Resolving interference when merging models,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Ties-merging: Resolving interference when merging models,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:34.698843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fa21d37b-a771-4449-91a6-3435eabc61af · outbound

This paper cites Language models are super mario: Absorbing abili- ties from homologous models as a free lunch,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Language models are super mario: Absorbing abili- ties from homologous models as a free lunch,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:34.530162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 398b79e7-8644-427f-8e5f-373c2ca90aa7 · outbound

This paper cites Unsupervised cross-lingual representation learning for speech recognition,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Unsupervised cross-lingual representation learning for speech recognition,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:34.214728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ee97c285-be2d-4cfc-9488-fdd2a8c1f61e · outbound

This paper cites Genetic k-means algo- rithm,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Genetic k-means algo- rithm,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:34.005818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e8b373b7-9440-499e-9f3f-ac2a5e5cc222 · outbound

This paper cites Hifi-gan: Generative adversarial networks for ef- ficient and high fidelity speech synthesis,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Hifi-gan: Generative adversarial networks for ef- ficient and high fidelity speech synthesis,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:33.827520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b653935a-2441-401d-aa7f-9a6b82a1fdf8 · outbound

This paper cites Librispeech: An asr corpus based on pub- lic domain audio books,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Librispeech: An asr corpus based on pub- lic domain audio books,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:33.654700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6d9ed3fb-bc8b-41fc-a9b7-ad04edf37432 · outbound

This paper cites Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:32.064798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85e25b7a-f8e9-46c9-94ef-00a99ae95432 · outbound

This paper cites SpeechT5: Unified-modal encoder- decoder pre-training for spoken language processing,.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models SpeechT5: Unified-modal encoder- decoder pre-training for spoken language processing,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:49:33.424292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 578e6321-953e-4e70-9458-bd1ed3843068 · outbound

This paper cites Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:32.437237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3951a82a-26f5-4487-8216-8f763123e084 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Instruction-Following Evaluation for Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:49:32.643541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 118b8495-b3c1-4f18-bd1f-c222269dc67c · inbound