4arXiv cs.CL (Computation and Language)·
Latent-IM: Recovering dialogue management control inside speech LLMs via latent interaction management
Researchers introduce Latent-IM, a framework that recovers an internal analogue of classical dialogue management (state estimation and action control) within LLMs for spoken dialogue systems. The approach formulates conversational move control as two coupled problems—selection and realization—and provides a general interface for steering conversational moves at generation time without full fine-tuning. On the task of reproducing human conversational move choices, Latent-IM improves average end-to-end move accuracy by 12.5 points over an unsteered backbone while matching fine-tuning performance.
Related guides (1)
Related events (8)
RL-based alignment improves interactivity in full-duplex spoken dialogue models
Researchers propose a post-training alignment method using reinforcement learning to improve interactivity in full-duplex spoken dialogue models, which can listen and speak simultaneously. The method addresses four canonical axes of interactivity—pause handling, turn-taking, backchanneling, and user interruption—each with axis-specific reward functions, plus an LLM-based reward to prevent semantic degradation. The approach is applied to two open-source models, Moshi and PersonaPlex, showing consistent improvements in both offline and real-time multi-turn evaluation.
IMLogic benchmark and RootMem framework target implicit logical memory retrieval for personalized LLMs
Researchers introduce IMLogic, a benchmark for evaluating implicit logical memory retrieval in long-dialogue personalized LLM scenarios, addressing gaps in existing semantic-similarity-based retrieval methods. They also propose RootMem, a plug-and-play framework that distills user histories into structured 'root memories' and uses an LLM-based router to activate logically relevant memories alongside semantic retrieval. Experiments show RootMem outperforms retrieval baselines and improves existing memory agents. The work targets a concrete weakness in current personalized LLM memory systems where logically critical memories lack semantic overlap with queries.
IFLLM dataset uses mouse and eye-tracking signals to improve LLM alignment via implicit feedback
Researchers introduce IFLLM, a dataset of 1,336 multi-turn interactions from 59 Mechanical Turk workers capturing mouse trajectories and webcam-derived eye gaze to study implicit user feedback for LLM alignment. A reward model trained on this implicit feedback improves text-based reward model accuracy from 55% to 64% and nearly triples relative response quality improvements when combined with DPO across eight LLMs. The work addresses the scarcity and cost of explicit preference annotations by mining behavioral signals already present in user interactions.
Audio Interaction Model: Unified Streaming LALM with Always-On Perceive-Decide-Respond Loop
Researchers introduce the Audio Interaction Model framework and a concrete implementation called Audio-Interaction, a unified streaming Large Audio Language Model that handles both offline tasks and real-time audio interaction through a continuous perceive-decide-respond loop. The system is built on SoundFlow, a framework covering data construction, training, and asynchronous low-latency inference. The authors also release StreamAudio-2M, a 2.6M-item streaming corpus spanning 28 sub-tasks, and Proactive-Sound-Bench for evaluating proactive audio intervention. Evaluated across 8 benchmarks, the model preserves competitive offline performance while enabling real-time ASR, streaming instruction following, and proactive response capabilities not available in prior offline LALMs.
Synthetic LLM-generated conversations improve ASR training for low-resource languages
Researchers propose a pipeline that uses LLMs to generate scenario-level dialogues and TTS to synthesize multi-speaker audio, creating simulated conversational training data for ASR systems. Evaluated on the Hungarian BEA-Dialogue benchmark, a model trained on 67 hours of real plus 636 hours of synthetic data outperforms a zero-shot model trained on 2,700 hours of real Hungarian speech. The study tests five LLM families under multiple budget and mixing configurations using a FastConformer-Large backbone, finding that generator choice and data composition significantly affect gains.
Interleaved speech-text LMs implicitly transcribe speech in intermediate layers before predicting in text space
A new arXiv paper analyzes the internal mechanisms of interleaved speech-text language models using the logit lens, revealing that these models undergo an implicit transcription phase in intermediate layers where the text token of a spoken word becomes decodable despite no explicit speech recognition training. This transcription appears as a top candidate word for up to 77% of the data, after which the model predicts the next word in text space before converting back to speech. The findings illuminate how speech and text modalities interact in the latent space of SLMs and have implications for optimizing speech language model training.
BayLing-Duplex: Native full-duplex speech dialogue using a single autoregressive LLM
Researchers introduce BayLing-Duplex, a speech language model that achieves native full-duplex interaction — simultaneous listening and speaking — using a single autoregressive LLM with no auxiliary VAD or turn-taking module. Built by fine-tuning GLM-4-Voice on 400K samples plus a lightweight DPO stage, it reaches 92% turn-taking success and 100% interruption success on InstructS2S-Eval, and improves speech-response quality substantially over Moshi. The approach adds only special tokens to the standard vocabulary, making it portable across LLM architectures without architectural changes.
Counterfactual context revision framework for auditing LLM-based stance simulation in online discussions
Researchers introduce a counterfactual context revision framework to audit how LLMs simulate individual users' stances in online discussions. By applying controlled text-only and multimodal (meme-based) revisions to conversational contexts, they measure how readily simulated stances shift in response to semantically independent changes. Results show effective and robust stance transitions across both revision types and polarization-preference mechanisms, raising concerns about whether LLM simulations reflect genuine user-specific beliefs or are highly context-sensitive artifacts. The work contributes an evaluation framework and highlights risks of using LLMs to model online opinion dynamics.