mlsanityData to 14 Oct 2026

SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information

arXiv 2505.13237 ↗First posted 19 May 2025eess.AS cs.CL cs.SDcited by 42

On the map: LLM reasoning → Audio-language model reasoning

Abstract (arXiv)

Large audio-language models (LALMs) extend the large language models with multimodal understanding in speech, audio, etc. While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities remain underexplored. Particularly, their multi-hop reasoning, the ability to recall and integrate multiple facts, lacks systematic evaluation. Existing benchmarks focus on general speech and audio-processing tasks, conversational abilities, and fairness but overlook this aspect. To bridge this gap, we introduce SAKURA, a benchmark assessing LALMs' multi-hop reasoning based on speech and audio information. Results show that LALMs struggle to integrate speech/audio representations for multi-hop reasoning, even when they extract the relevant information correctly, highlighting a fundamental challenge in multimodal reasoning. Our findings expose a critical limitation in LALMs, offering insights and resources for future research.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 39 of its 42 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

39 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark24 Oct
  2. 2024GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities17 Jun
  3. 2023CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models12 Oct

Other references · 36

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  6. 2024A Survey on LLM-as-a-Judgecited by 1,423
  7. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  10. 2018MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversationscited by 643
  11. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  12. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
24 more
  1. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  2. 2024Qwen2-Audio Technical Reportcited by 560
  3. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 506
  4. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 265
  5. 2024AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehensioncited by 220
  6. 2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 173
  7. 2024Do Large Language Models Latently Perform Multi-Hop Reasoning?cited by 169
  8. 2017Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networkscited by 102
  9. 2023Joint Audio and Speech Understandingcited by 100
  10. 2024Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queriescited by 78
  11. 2024A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasonerscited by 73
  12. 2024Premise Order Matters in Reasoning with Large Language Modelscited by 72
  13. 2024Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Taskscited by 71
  14. 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Wordscited by 68
  15. 2024Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversationscited by 45
  16. 2024DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Datacited by 45
  17. 2024Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Modelscited by 31
  18. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  19. 2024Building a Taiwanese Mandarin Spoken Language Model: A First Attemptcited by 23
  20. 2024Distributional reasoning in LLMs: Parallel reasoning processes in multi-hop reasoningcited by 21
  21. 2024Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Modelscited by 21
  22. 2024Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Modelscited by 16
  23. 2025A Preliminary Exploration with GPT-4o Voice Modecited by 16
  24. 2024Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Modelscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 26.

42 papers.

Sort:

By area:

  1. 2025DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignmentcited by 50
  2. 2025Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Surveycited by 39
  3. 2025Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decodingcited by 24
  4. 2025AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Modelscited by 18
  5. 2025MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talkscited by 14
  6. 2025EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Modelscited by 11
  7. 2026All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluationcited by 8
  8. 2025From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Datacited by 7
  9. 2026The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agentscited by 6
  10. 2026How Contrastive Decoding Enhances Large Audio Language Modelscited by 6
  11. 2025Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understandingcited by 5
  12. 2025Hearing the Order: Investigating Position Bias in Large Audio-Language Modelscited by 5
30 more
  1. 2025Robustness assessment of large audio language models in multiple-choice evaluationcited by 5
  2. 2025SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Modelscited by 5
  3. 2026Causal Tracing of Audio-Text Fusion in Large Audio Language Modelscited by 5
  4. 2025When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Modelscited by 4
  5. 2025Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variationscited by 4
  6. 2026Towards Robust Speech Deepfake Detection via Human-Inspired Reasoningcited by 4
  7. 2026Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Modelscited by 4
  8. 2026Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoningcited by 3
  9. 2025ORCA: Open-ended Response Correctness Assessment for Audio Question Answeringcited by 2
  10. 2026MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Modelscited by 2
  11. 2026Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Modelscited by 2
  12. 2026How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluationcited by 2
  13. 2025Investigating Faithfulness in Large Audio Language Modelscited by 1
  14. 2025TAU: A Benchmark for Cultural Sound Understanding Beyond Semanticscited by 1
  15. 2026Do What I Say: A Spoken Prompt Dataset for Instruction-Followingcited by 1
  16. 2026HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Modelscited by 1
  17. 2026Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Interventioncited by 1
  18. 2026RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmarkcited by 1
  19. 2026Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Modelscited by 1
  20. 2026From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Modelscited by 1
  21. 2026Enhancing Audio Reasoning via Semantic Summary Predictioncited by 1
  22. 2026When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removalcited by 0
  23. 2026SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Modelscited by 0
  24. 2026Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognitioncited by 0
  25. 2026ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judgecited by 0
  26. 2026Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Modelscited by 0
  27. 2026Large Audio Language Models for Spoofing-Aware Speaker Verificationcited by 0
  28. 2026ESCUCHA: A Spanish Speech Benchmark for Heterogeneous Acoustic Conditionscited by 0
  29. 2026Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputscited by 0
  30. 2026AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
  2. 2026A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models
  3. 2026Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents
  4. 2025Mellow: a small audio language model for reasoning
  5. 2026Multi-Source Evidence Fusion for Audio Question Answering
  6. 2025Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
  7. 2025SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models
  8. 2026ALARM: Audio-Language Alignment for Reasoning Models