Efficient and robust turn-taking detection remains a significant challenge in industrial-grade voice AI agents. Existing systems often rely on acoustic or linguistic cues alone, limiting accuracy and stability, whereas directly endowing large language models with full-duplex capability incurs heavy data and deployment...
Yu Pan, Guangzhao Yang, Muhammad Huzaifah et al.· 0 citations
Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online information ecosystem, yet prevailing approaches rely on labeled entity roles and rigid predefined schemas that fail to capture the diffuse and context-dependent nature of participati...
Diego Revilla, Martin Fernandez-de-Retana, Lingfeng Chen et al.· 0 citations
Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by their own perceptual findings or missing logically entailed conclusions. Standard lexical metrics heavily penalize clinical paraphrasing and...
Vikash Singh, Debargha Ganguly, Haotian Yu et al.· 0 citations
We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer models, we run two experimental paradigms -- similarity-based forced choice and free association -- over a shared 5,000-word vocabulary, collec...
Louis Schiekiera, Max Zimmer, Christophe Roux et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce verification-guided answers through iterative refinement. Our approach decomposes...
Vikash Singh, Darion Cassel, Nathaniel Weir et al.· 0 citations
Counterfactual storytelling exposes LLM shortcomings in causal reasoning, where few-shot prompting and SFT fail to produce logical and rational narratives. This case study introduces Retell, Reward, Repeat (RRR), a narrative theory-informed RL pipeline that teaches causal story structure. We extend an existing counterf...
David Y. Liu, Xanthe Muston, Dipankar Srirag et al.· 0 citations
Foundation models are used for many real-world applications involving language understanding and generation from temporally-ordered multimodal events. In this work, we study the ability of models to identify the most important sub-events in a video, which is a fundamental prerequisite for summarizing, reasoning over, o...
Aditya K Surikuchi, Raquel Fern\'andez, Sandro Pezzelle· 0 citations
This work provides the first systematic investigation into probing model internals across a conversation trajectory, moving beyond static, single-prompt analysis to capture the evolving state of privacy-sensitive interactions, and illustrating their applicability across contexts, attack styles, multiple base models, an...
Large language models (LLMs) often produce judgments similar to those of humans, but their interpretation of figurative language remains unclear. We compared human participants and four instruction-tuned LLMs (GPT-4, Gemma-2-9B, Llama-3.2, and Mistral-7B) on their ratings of 240 dialogue-based sentences spanning six li...
Samhita Bollepally, Aurora Sloman-Moll, Takashi Yamauchi et al.· 0 citations
Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable control of complex, behavior-level semantic attributes in language generation. In...
Applying well-established statistical methods effectively to LLM evals requires consideration of model correlations and prediction noises. Leading evals often ignore data noise, have low statistical power, or make unnecessary trade-offs. We define and measure three types of noise: 1) prediction noise from generating di...
Prompt injection can cause large language models (LLMs) to deviate from their intended tasks by following instructions embedded in untrusted input. We investigate whether changing a classifier's output labels improves accuracy under such attacks, using sentiment classification as a case study. Label Disguise Defense (L...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
