Mind the Gap! Static and Interactive Evaluations of Large Audio Models

As AI chatbots become ubiquitous, voice interaction presents a compelling way to enable rapid, high-bandwidth communication for both semantic and social signals. This has driven research into Large Audio Models (LAMs) to power voice-native experiences. However, aligning LAM development with user goals requires a clear understanding of user needs and preferences to establish reliable progress metrics. This study addresses these challenges by introducing an interactive approach to evaluate LAMs and collecting 7,500 LAM interactions from 484 participants. Through topic modeling of user queries, we identify primary use cases for audio interfaces. We then analyze user preference rankings and qualitative feedback to determine which models best align with user needs. Finally, we evaluate how static benchmarks predict interactive performance - our analysis reveals no individual benchmark strongly correlates with interactive results ($\tau \leq 0.33$ for all benchmarks). While combining multiple coarse-grained features yields modest predictive power ($R^2$=$0.30$), only two out of twenty datasets on spoken question answering and age prediction show significantly positive correlations. This suggests a clear need to develop LAM evaluations that better correlate with user preferences.

Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responses

This study quantitively examines which features of AI-generated text lead humans to perceive subjective consciousness in large language model (LLM)-based AI systems. Drawing on 99 passages from conversations with Claude 3 Opus and focusing on eight features -- metacognitive self-reflection, logical reasoning, empathy, emotionality, knowledge, fluency, unexpectedness, and subjective expressiveness -- we conducted a survey with 123 participants. Using regression and clustering analyses, we investigated how these features influence participants' perceptions of AI consciousness. The results reveal that metacognitive self-reflection and the AI's expression of its own emotions significantly increased perceived consciousness, while a heavy emphasis on knowledge reduced it. Participants clustered into seven subgroups, each showing distinct feature-weighting patterns. Additionally, higher prior knowledge of LLMs and more frequent usage of LLM-based chatbots were associated with greater overall likelihood assessments of AI consciousness. This study underscores the multidimensional and individualized nature of perceived AI consciousness and provides a foundation for better understanding the psychosocial implications of human-AI interaction.

From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants

The Adobe Experience Platform AI Assistant is a conversational tool that enables organizations to interact seamlessly with proprietary enterprise data through a chatbot. However, due to access restrictions, Large Language Models (LLMs) cannot retrieve these internal documents, limiting their ability to generate accurate zero-shot responses. To overcome this limitation, we use a Retrieval-Augmented Generation (RAG) framework powered by a Knowledge Graph (KG) to retrieve relevant information from external knowledge sources, enabling LLMs to answer questions over private or previously unseen document collections. In this paper, we propose a novel approach for building a high-quality, low-noise KG. We apply several techniques, including incremental entity resolution using seed concepts, similarity-based filtering to deduplicate entries, assigning confidence scores to entity-relation pairs to filter for high-confidence pairs, and linking facts to source documents for provenance. Our KG-RAG system retrieves relevant tuples, which are added to the user prompts context before being sent to the LLM generating the response. Our evaluation demonstrates that this approach significantly enhances response relevance, reducing irrelevant answers by over 50% and increasing fully relevant answers by 88% compared to the existing production system.

Prompt-to-Leaderboard

Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance. To address this, we propose Prompt-to-Leaderboard (P2L), a method that produces leaderboards specific to a prompt. The core idea is to train an LLM taking natural language prompts as input to output a vector of Bradley-Terry coefficients which are then used to predict the human preference vote. The resulting prompt-dependent leaderboards allow for unsupervised task-specific evaluation, optimal routing of queries to models, personalization, and automated evaluation of model strengths and weaknesses. Data from Chatbot Arena suggest that P2L better captures the nuanced landscape of language model performance than the averaged leaderboard. Furthermore, our findings suggest that P2L's ability to produce prompt-specific evaluations follows a power law scaling similar to that observed in LLMs themselves. In January 2025, the router we trained based on this methodology achieved the \#1 spot in the Chatbot Arena leaderboard. Our code is available at this GitHub link: https://github.com/lmarena/p2l.

Enhancing Smart Environments with Context-Aware Chatbots using Large Language Models

This work presents a novel architecture for context-aware interactions within smart environments, leveraging Large Language Models (LLMs) to enhance user experiences. Our system integrates user location data obtained through UWB tags and sensor-equipped smart homes with real-time human activity recognition (HAR) to provide a comprehensive understanding of user context. This contextual information is then fed to an LLM-powered chatbot, enabling it to generate personalised interactions and recommendations based on the user's current activity and environment. This approach moves beyond traditional static chatbot interactions by dynamically adapting to the user's real-time situation. A case study conducted from a real-world dataset demonstrates the feasibility and effectiveness of our proposed architecture, showcasing its potential to create more intuitive and helpful interactions within smart homes. The results highlight the significant benefits of integrating LLM with real-time activity and location data to deliver personalised and contextually relevant user experiences.

Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health

Despite the prevalence of sleep-tracking devices, many individuals struggle to translate data into actionable improvements in sleep health. Current methods often provide data-driven suggestions but may not be feasible and adaptive to real-life constraints and individual contexts. We present HealthGuru, a novel large language model-powered chatbot to enhance sleep health through data-driven, theory-guided, and adaptive recommendations with conversational behavior change support. HealthGuru's multi-agent framework integrates wearable device data, contextual information, and a contextual multi-armed bandit model to suggest tailored sleep-enhancing activities. The system facilitates natural conversations while incorporating data-driven insights and theoretical behavior change techniques. Our eight-week in-the-wild deployment study with 16 participants compared HealthGuru to a baseline chatbot. Results show improved metrics like sleep duration and activity scores, higher quality responses, and increased user motivation for behavior change with HealthGuru. We also identify challenges and design considerations for personalization and user engagement in health chatbots.

Investigating Non-Transitivity in LLM-as-a-Judge

Automatic evaluation methods based on large language models (LLMs) are emerging as the standard tool for assessing the instruction-following abilities of LLM-based agents. The most common method in this paradigm, pairwise comparisons with a baseline model, critically depends on the assumption of transitive preferences. However, the validity of this assumption remains largely unexplored. In this study, we investigate the presence of non-transitivity within the AlpacaEval framework and analyze its effects on model rankings. We find that LLM judges exhibit non-transitive preferences, leading to rankings that are sensitive to the choice of the baseline model. To mitigate this issue, we show that round-robin tournaments combined with Bradley-Terry models of preference can produce more reliable rankings. Notably, our method increases both the Spearman correlation and the Kendall correlation with Chatbot Arena (95.0% -> 96.4% and 82.1% -> 86.3% respectively). To address the computational cost of round-robin tournaments, we propose Swiss-Wise Iterative Matchmaking (Swim) tournaments, using a dynamic matching strategy to capture the benefits of round-robin tournaments while maintaining computational efficiency.

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However, existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization. Our analysis reveals that programs submitted to LLM serving engines experience long cumulative wait times, primarily due to head-of-line blocking at both the individual LLM request and the program. To address this, we introduce Autellix, an LLM serving system that treats programs as first-class citizens to minimize their end-to-end latencies. Autellix intercepts LLM calls submitted by programs, enriching schedulers with program-level context. We propose two scheduling algorithms-for single-threaded and distributed programs-that preempt and prioritize LLM calls based on their programs' previously completed calls. Our evaluation demonstrates that across diverse LLMs and agentic workloads, Autellix improves throughput of programs by 4-15x at the same latency compared to state-of-the-art systems, such as vLLM.

REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation

Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research relies on synthetic, LLM-generated data, leaving open questions about real-world conversational patterns. To address this gap, we introduce REALTALK, a 21-day corpus of authentic messaging app dialogues, providing a direct benchmark against genuine human interactions. We first conduct a dataset analysis, focusing on EI attributes and persona consistency to understand the unique challenges posed by real-world dialogues. By comparing with LLM-generated conversations, we highlight key differences, including diverse emotional expressions and variations in persona stability that synthetic dialogues often fail to capture. Building on these insights, we introduce two benchmark tasks: (1) persona simulation where a model continues a conversation on behalf of a specific user given prior dialogue context; and (2) memory probing where a model answers targeted questions requiring long-term memory of past interactions. Our findings reveal that models struggle to simulate a user solely from dialogue history, while fine-tuning on specific user chats improves persona emulation. Additionally, existing models face significant challenges in recalling and leveraging long-term context within real-world conversations.

KL Penalty Control via Perturbation for Direct Preference Optimization

Direct Preference Optimization (DPO) demonstrates the advantage of aligning a large language model with human preference using only an offline dataset. However, DPO has the limitation that the KL penalty, which prevents excessive deviation from the reference model, is static throughout the training process. Several methods try to turn this static KL penalty into a dynamic one, but no approach can adaptively assign different KL penalties for each preference pair. In this paper, we propose $\varepsilon$-Direct Preference Optimization ($\varepsilon$-DPO), which allows adaptive control of the KL penalty strength $\beta$ for each preference pair. Specifically, $\varepsilon$-DPO adaptively controls $\beta$ for each preference pair based on the monotonicity of logits as a preference model under the perturbation of $\beta$ during training by simply reusing the logit of the current policy and the reference policy. Experimental results show that $\varepsilon$-DPO outperforms existing direct alignment algorithms and KL penalty relaxation methods on general chatbot benchmarks, highlighting the significance of adaptive KL penalty relaxation at the instance-level in DPO.