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.
Related guides (2)
Related events (8)
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.
ModeratorLM: Role-conditioned turn-taking for multi-party voice agents with 40%+ precision gains
Researchers introduce ModeratorLM, a voice agent system that conditions turn-taking behavior on an explicitly assigned conversational role in multi-party settings, built on a streaming speech LLM. A reasoning-augmented variant adds chain-of-thought over conversational context. Evaluated on real-world meeting data and the new RolePlayConv synthetic dataset, the system achieves over 40% improvement in turn-taking precision and 70% in recall while reducing false-positive interruptions versus non-role-conditioned baselines.
Aligning language models to follow instructions
OpenAI published a blog post describing their work on aligning language models to follow human instructions, corresponding to the InstructGPT research. This work introduced reinforcement learning from human feedback (RLHF) as a core technique for training models to be more helpful, honest, and aligned with user intent. The approach demonstrated that smaller instruction-tuned models could outperform larger base models on human preference evaluations, marking a foundational shift in how language models are trained and deployed.
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.
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.
AlignAtt4LLM adapts simultaneous speech translation policy to decoder-only LLMs for IWSLT 2026
Researchers present AlignAtt4LLM, a simultaneous speech translation system for IWSLT 2026 covering English to German, Italian, and Chinese. The system cascades Qwen3-ASR for incremental transcription with Gemma-4 E4B-it for translation, applying a novel AlignAtt policy adapted for decoder-only LLMs that lack encoder-decoder cross-attention. Key contributions include explicit source span prompting, offline alignment head selection, and query/key capture to recover a usable attention-based read/write policy. The system outperforms IWSLT 2026 baselines for European language pairs in both low- and high-latency regimes.
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.
ContextRL: Context-aware reinforcement learning improves grounding in agentic and multimodal LLMs
Researchers introduce ContextRL, a reinforcement learning method that trains LLMs to select the context that supports a given query-answer pair from two highly similar candidates, rather than supervising only final answers. The approach constructs contrastive context pairs in two domains: coding agent trajectories (1k pairs) and multimodal image pairs (7k pairs). ContextRL achieves +2.2% average gains over standard GRPO on 5 long-horizon benchmarks and +1.8% across 12 visual QA benchmarks, with ablations showing the gains stem from the context-selection objective rather than the contrastive data alone.