Cover Image

Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Modica, Luca, Landin, Filip, Farahani, Mehrdad, Qian, Livia, Skantze, Gabriel, Johansson, Richard
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

To Copy or Not to Copy: Copying Is Easier to Induce Than Recall
by: Farahani, Mehrdad, et al.
Published: (2026)

Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models
by: Farahani, Mehrdad, et al.
Published: (2024)

Joint Learning of Context and Feedback Embeddings in Spoken Dialogue
by: Qian, Livia, et al.
Published: (2024)

Aligning Backchannel and Dialogue Context Representations via Contrastive LLM Fine-Tuning
by: Qian, Livia, et al.
Published: (2026)

Representation of perceived prosodic similarity of conversational feedback
by: Qian, Livia, et al.
Published: (2025)

Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
by: Willemsen, Bram, et al.
Published: (2025)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
by: Lv, Ang, et al.
Published: (2024)

VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency
by: Torgashov, Nikita, et al.
Published: (2025)

Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
by: Saynova, Denitsa, et al.
Published: (2024)

Geometric Factual Recall in Transformers
by: Ravfogel, Shauli, et al.
Published: (2026)

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
by: Liu, Yihong, et al.
Published: (2026)

Applying General Turn-taking Models to Conversational Human-Robot Interaction
by: Skantze, Gabriel, et al.
Published: (2025)

How Well Do Large Language Models Disambiguate Swedish Words?
by: Johansson, Richard
Published: (2024)

Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation
by: Dejl, Adam, et al.
Published: (2025)

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
by: Chughtai, Bilal, et al.
Published: (2024)

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
by: Wang, Yifei, et al.
Published: (2024)

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
by: Liu, Xiyu, et al.
Published: (2024)

Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding
by: Willemsen, Bram, et al.
Published: (2024)

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline
by: Lu, Meng, et al.
Published: (2025)

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
by: Yang, Jiayu, et al.
Published: (2025)

SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models
by: Cheng, Xianfu, et al.
Published: (2025)

"Dyadosyncrasy", Idiosyncrasy and Demographic Factors in Turn-Taking
by: Cavalcanti, Julio Cesar, et al.
Published: (2025)

Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models
by: Wang, Yu, et al.
Published: (2025)

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
by: Calderon, Nitay, et al.
Published: (2026)

Understanding Factual Recall in Transformers via Associative Memories
by: Nichani, Eshaan, et al.
Published: (2024)

Can VLMs Recall Factual Associations From Visual References?
by: Ashok, Dhananjay, et al.
Published: (2025)

Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
by: Smith, Matthew L., et al.
Published: (2026)

Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
by: Jafari, Nazanin, et al.
Published: (2026)

Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall
by: Yuan, Jiaqing, et al.
Published: (2024)

Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
by: Wang, Qianli, et al.
Published: (2025)

CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
by: Du, Yexing, et al.
Published: (2025)

An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation
by: Mahapatra, Joy, et al.
Published: (2024)

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
by: Zhang, Zhuoran, et al.
Published: (2024)

Grounded Visual Factualization: Factual Anchor-Based Finetuning for Enhancing MLLM Factual Consistency
by: Morbiato, Filippo, et al.
Published: (2025)

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
by: Fastowski, Alina, et al.
Published: (2025)

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
by: Ramprasad, Sanjana, et al.
Published: (2024)

How Do Large Language Models Acquire Factual Knowledge During Pretraining?
by: Chang, Hoyeon, et al.
Published: (2024)

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
by: Xiang, Bajian, et al.
Published: (2025)

Tracing Relational Knowledge Recall in Large Language Models
by: Popovič, Nicholas, et al.
Published: (2026)

Functional Abstraction of Knowledge Recall in Large Language Models
by: Wang, Zijian, et al.
Published: (2025)