paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Cloud-ScPO: Hidden-State Geometry for Semi-Supervised Preference Optimization in LLM Reasoning

Yuzhou Liu, Xiyang Hu

Preference optimization improves mathematical reasoning in large language models (LLMs), but reliable chosen-rejected pairs usually require verified answers, human annotations, or external reward models. We investigate whether preference supervision can instead be derived from the model's internal representation geometry in a semi-supervised setting. Our analysis shows that reasoning trajectories generated across different mathematical problems form structured global point clouds in which correct and incorrect trajectories exhibit different geometric organization. Based on this observation, we propose Cloud-ScPO, a topology-guided preference-mining framework that uses a small labeled set to construct multiple correct and incorrect reference Clouds. Each trajectory is represented by a mean-pooled hidden state and scored against connectivity-induced components using a component-level soft $k$-nearest-neighbor measure averaged across reference banks. We combine this cross-problem Cloud signal with prompt-level self-consistency: self-consistency determines the answer-level preference direction, while Cloud scoring selects concrete trajectories and filters pairs by their score margin. Experiments on GSM8K and MATH-Numeric across four model settings show that Cloud-ScPO consistently improves over ScPO, with gains of up to 4.49% on GSM8K and 4.19% on MATH-Numeric. Pair-level analyses further show that Cloud-ScPO maintains comparable correctness reliability while more effectively separating informative chosen trajectories from incomplete, repetitive, or otherwise low-quality rejected responses.

arXiv

RepBench: Compiling Benchmarks into Capability Representations for Large Language Models

Yanshi Li, Xueru Bai, Shuman Liu, Long Zhang

Representation engineering reads and steers capability directions in large language models, yet methods are typically evaluated on paper-specific synthetic data. The resulting measurements are difficult to compare or reproduce and may reflect surface patterns rather than capabilities. We present RepBench, a benchmark-grounded data layer for capability-aligned representation probing. Crawling 13,427 benchmark papers yields a taxonomy of 182 capability clusters in 13 families; harvesting 353 public benchmark datasets yields 46,149 audited probe texts covering 94 capabilities, each supported by at least two independent benchmarks. This multi-benchmark design reduces dependence on any single source: raw per-text vectors exhibit no natural cluster granularity, whereas benchmark-pooled capability vectors show an interior clustering optimum at a small number of clusters on all 12 evaluated models, with low agreement to the human taxonomy. Under cross-benchmark transfer evaluation across twelve models completed by all four readouts, difference-in-means attains the highest model-level mean on ten models, while logistic regression wins the most capability-model cells. This disagreement shows that the readout method and aggregation criterion are meaningful evaluation dimensions. The pipeline, corpus, and evaluation code are released as a reusable closed-loop workflow.

arXiv

Kalypso: Relational LLM Serving

Hojae Son, Md Ashraful Islam, Huy Gia Cao, Hui Guan, Marco Serafini

Large language models are increasingly used as semantic operators for filtering, extracting, ranking, joining, and transforming unstructured data. Existing semantic query processing systems invoke request-centric LLM serving systems that are unaware of the query plan, leaving substantial performance opportunities unused. This paper introduces relational LLM serving, an abstraction that makes LLM serving aware of semantic query structure while preserving query semantics and output accuracy. The key opportunity is pipelined execution across semantic operators: when intermediate tuples flow directly from one operator to the next, their KV-cache state can be reused instead of recomputed. We present Kalypso, a relational LLM serving system that exposes an API for semantic query plans and executes them using an adaptive, memory-aware scheduling algorithm. Kalypso addresses a new online scheduling problem in which pipelined operator execution is coupled with GPU memory pressure management to reuse KV-cache state in the serving engine before eviction. Its scheduler continuously adjusts memory allocations to balance upstream parallelism, downstream progress, and GPU utilization. Our evaluation shows that Kalypso improves query completion time over baselines using request-centric LLM serving, with speedups up to 4.57x across diverse workloads, demonstrating that query-aware LLM serving can substantially improve the efficiency of semantic query execution.

arXiv

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Qingyu Zhang, Qianhao Yuan, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Ming Xu, Jiarui Li

Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires. Two observations trace this gap. First, greedy \textsc{pass}@$1$ nearly vanishes after compression, yet \textsc{pass}@$k$ recovers substantially under repeated sampling: useful generations are demoted, not erased. Second, the recoverable regime fails mainly through suffix repetition. Recovery should therefore train on the compressed model's own on-policy states with dense token-level supervision, which On-Policy Distillation (OPD) provides by reusing the pre-compression model as a frozen teacher. However, long on-policy rollouts spend early recovery budget on low-information repetitive suffixes, delaying loss descent. To mitigate this waste, we propose \textbf{\shortopd}, a short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes, treats the surviving prefix as each rollout's effective length, and allocates future rollout budgets to the effective lengths the policy can currently use. Across math, code, and open-ended generation, \shortopd\ raises the compressed model's score to about $9\times$ its unrecovered value and $1.6$--$4.4\times$ standard recovery recipes (SFT w/o KD, KD, and SeqKD), and it matches a fixed $8192$-token rollout horizon within two points using a quarter of the training time ($8.5$ vs.\ $35.9$ hours) and $71\%$ fewer rollout tokens. We hope this recipe helps move structured pruning beyond marginal gains on perplexity and multiple-choice benchmarks, a step closer to deployment-ready generation quality.

arXiv

TypeProbe: Recovering Type Representations from Hidden States of Pre-trained Code Models

Giuliano Gorgone, Fausto Carcassi

State-of-the-art code models achieve impressive performance, yet the extent to which they internally encode type information remains poorly understood. We probe the residual streams of pretrained code models for internal type representations using a parallel dataset of Java and Python code examples. Our results show that cross-lingual type representations emerge even from untyped code. Moreover, we test whether hidden states linearly encode the result type implied by typed function application by training probes on one language to infer argument and result types in the other. Finally, we find that this structure is partly robust to lexical perturbations and cross-language syntactic variations. To the best of our knowledge, prior work on interpretability of code models has not directly targeted formal type semantics or cross-lingual type representations. We release our code and datasets.

arXiv

Adapting Foundation ASR Models to Dysarthric Speech: A Case Study

Christian Huber, Laura Kernahan, Alexander Waibel

Automatic speech recognition (ASR) systems often perform poorly in dysarthric speech, limiting their usefulness to affected speakers in everyday communication. This paper presents a personalized ASR system for a dysarthric speaker, built by adapting a foundation ASR model to speaker-specific data. Using the TEQST tool, we collected 92 hours of read speech and later added 8.8 hours of user corrections gathered through a deployed mobile application. Starting from Whisper, fine-tuning reduced word error rate to 15.8% with only 1.4 hours of adaptation data on the read test set, reached 10.7% / 16.1% with 22.5 hours on the read and corrections test sets, respectively, and achieved the best result of 9.7% when using all available data including the corrections on the read test set and 7.8% on the corrections test set. Using LoRA adaptation and/or Qwen3-ASR as foundation model performed worse in this setting. The results show that personalized fine-tuning can make foundation ASR models substantially more effective for dysarthric speech and suitable for practical deployment.

arXiv

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Soyeong Jeong, Jinheon Baek, Minki Kang, Sung Ju Hwang

Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.

arXiv

PhoneWorld: Scaling Phone-Use Agent Environments

Yuxuan Liu, Xin Lai, Junyi Li, Pengyuan Lyu, Jason, Yiduo Guo, Zhengyao Fang, Yang Ding, Yi Zhang, Weinong Wang, Huawen Shen, Xingran Zhou, Liang Wu, Fei Tang, Sunqi Fan, Shangpin Peng, Zheng Ruan, Anran Zhang, Chengquan Zhang, Han Hu, Benyou Wang, Ji-Rong Wen, Rui Yan, Zhengyang Tang

A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Existing mobile-agent benchmarks have made important progress on evaluation, but they do not by themselves provide a scalable way to construct many new phone-use environments. We present PhoneWorld, a reusable pipeline that converts real GUI trajectories and screenshots into controllable phone-use environments, executable tasks, automatic verifiers, and training rollouts. Rather than hand-building one mobile benchmark at a time, PhoneWorld uses real trajectories to recover which screens matter, how screens connect, which interactions must change environment state, and which user goals admit automatic verification. From these signals, it builds runnable mock Android apps backed by read-only app content and mutable state, then derives executable tasks, rule-based verifiers, and training rollouts from the same environments. In its current instantiation, PhoneWorld covers 34 apps across 16 domains, spanning common consumer mobile behaviors such as search, browsing, shopping, booking, media, and social interaction. Under a fixed training budget, replacing 10K steps from an auxiliary AndroidWorld corpus in an AndroidWorld-based baseline with broad PhoneWorld supervision improves all four evaluation benchmarks at once, raising HYMobileBench by 17.7 points, AndroidControl by 6.0 points, AndroidWorld by 14.7 points, and PhoneWorld by 52.5 points. We then study two additional scaling questions: increasing the amount of PhoneWorld supervision strongly improves PhoneWorld performance, and under a fixed PhoneWorld budget, expanding app coverage yields even larger gains. Overall, PhoneWorld shifts the focus from building one mobile benchmark at a time to scaling the supply of phone-use environments themselves.

arXiv

Fine-grained Claim-level RAG Benchmark for Law

Souvick Das, Sallam Abualhaija, Domenico Bianculli

The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-stake domains such as law, retrieval-augmented generation (RAG) is commonly used to mitigate hallucinations in generated responses. Nonetheless, prior work shows that RAG systems, whether general-purpose or legal-specific, still hallucinate at varying rates, making fine-grained evaluation essential. Despite the need, existing evaluation frameworks for legal RAG systems lack the granularity required to provide detailed analysis of retrieval and generation performance separately. Moreover, current benchmarks are largely English-only and centered on legal expert queries, overlooking non-expert needs. We introduce ClaimRAG-LAW, a comprehensive dataset for legal RAG that supports French and English, targets both experts and non-experts, and includes diverse question types reflecting realistic scenarios. We further apply a fine-grained evaluation framework of state-of-the-art legal RAG systems, revealing limitations in retrieval, generation, and claim-level analysis in the legal domain.

arXiv

When Gradient Importance Lies: Adaptive LoRA Rank Allocation Fails Under GRPO

Yash Ganpat Sawant

Adaptive rank allocation for LoRA - allocating more parameters to important layers and fewer to unimportant ones - consistently improves efficiency under supervised fine-tuning (SFT). We test whether this success transfers to reinforcement learning, specifically Group Relative Policy Optimization (GRPO). Using gradient-magnitude profiling on Qwen 2.5 1.5B with GSM8K, we find that, in our setting, it does not: proportional rank allocation degrades accuracy by 4.5 points compared to uniform allocation (70.0% vs. 74.5%), despite using identical parameter budgets. We identify two mechanisms behind this failure. First, the gradient landscape under GRPO is fundamentally flatter than under SFT: the max-to-min layer importance ratio is only 2.17x, whereas the layer concentration reported by Shi et al. (2024) for SFT (top 30% of layers carrying >80% of the gradient signal) implies a max/min ratio well above 10x. All layers carry meaningful gradient signal; none are truly idle. Second, we observe a gradient amplification effect: non-uniform allocation widens the importance spread from 2.17x to 3.00x, creating a positive feedback loop where high-rank layers absorb more gradient while low-rank layers are progressively silenced. A random-allocation control yields the same amplification (r=0.972 correlation between assigned rank and resulting gradient share), indicating that rank causally determines gradient importance rather than the reverse. The negative result is single-seed and single-task; we present it as preliminary evidence that gradient importance does not predict capacity requirements under RL, and that naive transfer of SFT-era rank allocation strategies to alignment training should be evaluated cautiously.

arXiv

Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization

Yash Ganpat Sawant

Stylistic personalization - making LLMs write in a specific individual's style, rather than merely adapting to task preferences - lacks evaluation grounded in authorship science. We show that grounding evaluation in authorship verification theory transforms what benchmarks can measure. Drawing on three measurement traditions - LUAR (a trained authorship verification model), an LLM-as-judge with decoupled trait matching, and classical function-word stylometrics - we evaluate four inference-time personalization methods across 50 authors and 1,000 generations. The theory-grounded metric (LUAR) provides what ad hoc alternatives cannot: calibrated baselines (human ceiling 0.756, cross-author floor 0.626) that give scores absolute meaning. All methods score below this floor (0.484-0.508), exposing an authorship gap invisible to uncalibrated metrics. The three metrics produce near-zero pairwise correlations (|r| < 0.07), confirming that without theoretical grounding, metric choice determines conclusions - an LLM judge declares a clear winner while LUAR finds no meaningful differentiation. These findings demonstrate the theory-benchmark cycle in action: authorship theory exposes evaluation failures that ad hoc benchmarks miss.

arXiv

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

Yoonsang Lee, Howard Yen, Xi Ye, Danqi Chen

We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into a final response. While such scaling has proven effective for chain-of-thought reasoning, agentic tasks pose unique challenges: trajectories are long, multi-turn, and tool-augmented, and outputs are often open-ended. Aggregating only final answers discards rich information from trajectories, while concatenating all trajectories exceeds the model's context window. To address this, we propose AggAgent, an aggregation agent that treats parallel trajectories as an environment. We equip it with lightweight tools to inspect candidate solutions and search across trajectories, enabling it to navigate and synthesize information on demand. Across six benchmarks and three model families (GLM-4.7, Qwen3.5, MiniMax-M2.5), AggAgent outperforms all existing aggregation methods-by up to 5.3% absolute on average and 10.3% on two deep research tasks-while adding minimal overhead, as the aggregation cost remains bounded by a single agentic rollout. Our findings establish agentic aggregation as an effective and cost-efficient approach to parallel test-time scaling.

arXiv

Learning to Interrupt in Language-based Multi-agent Communication

Danqing Wang, Da Yin, Ruta Desai, Lei Li, Asli Celikyilmaz, Ansong Ni

When a colleague starts explaining something you already understand, you interrupt them. This simple act, a listener taking control of the conversation, is natural in human communication but absent in current verbose LLM multi-agent systems. Current approaches address communication efficiency only from the speaker side, compressing messages before they are sent. We flip the perspective: rather than making speakers more concise, we let listeners decide when they have heard enough. We propose a new communication paradigm in which the listener can interrupt the speaker mid-generation. We find that LLMs, given this ability, are overconfident and interrupt too early before receiving sufficient information. This finding motivates HANDRAISER, a learning method that predicts the right moment to interrupt based on estimated future reward and communication cost. We evaluate our framework on three multi-agent tasks: 2-agent text pictionary, 3-agent meeting scheduling, and 3-agent debate. HANDRAISER reduces communication cost by 32.2% over the non-interruptible baseline while achieving comparable or superior task performance, with interruption behavior that generalizes across different agents and tasks.

arXiv

Early Stopping for Large Reasoning Models via Confidence Dynamics

Parsa Hosseini, Sumit Nawathe, Mahdi Salmani, Meisam Razaviyayn, Soheil Feizi

Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key challenge is determining when the model should stop reasoning and produce the final answer. In this work, we study the confidence of intermediate answers during reasoning and observe two characteristic behaviors: correct reasoning trajectories often reach high-confidence answers early, while incorrect rollouts tend to produce long, unproductive reasoning traces and exhibit less reliable confidence dynamics. Motivated by these observations, we propose CoDE-Stop (Confidence Dynamics Early Stop), an early stopping method that leverages the dynamics of intermediate answer confidence to decide when to terminate reasoning, requiring no additional training and easily integrating into existing models. We evaluate CoDE-Stop on diverse reasoning and science benchmarks across multiple models. Compared to prior early stopping methods, it achieves a more favorable accuracy-compute tradeoff and reduces total token usage by 25-50% compared to standard full-length reasoning. In addition, we provide analyses of confidence dynamics during reasoning, offering insights into how confidence changes in both correct and incorrect trajectories.

arXiv

Adaptive Stopping for Multi-Turn LLM Reasoning

Xiaofan Zhou, Huy Nguyen, Bo Yu, Chenxi Liu, Lu Cheng

Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by iteratively retrieving information, reasoning, or acting, but introduce a key challenge: \textbf{When should the model stop?} Existing approaches rely on heuristic stopping rules or fixed turn budgets and provide no formal guarantees that the final prediction still contains the correct answer. This limitation is particularly problematic in high-stakes domains such as finance and healthcare, where unnecessary turns increase cost and latency, while stopping too early risks incorrect decisions. Conformal prediction (CP) provides formal coverage guarantees, but existing LLM-CP methods only apply to a single model output and cannot handle multi-turn pipelines with adaptive stopping. To address this gap, we propose Multi-Turn Language Models with Conformal Prediction (MiCP), the first CP framework for multi-turn reasoning. MiCP allocates different error budgets across turns, enabling the model to stop early while maintaining an overall coverage guarantee. We demonstrate MiCP on adaptive RAG and ReAct, where it achieves the target coverage on both single-hop and multi-hop question answering benchmarks while reducing the number of turns, inference cost, and prediction set size. We further introduce a new metric that jointly evaluates coverage validity and answering efficiency.

arXiv

TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records

Dipankar Srirag, Quoc Dung Nguyen, Aditya Joshi, Padmanesan Narasimhan, Salil Kanhere

Research in emergency triage is restricted to structured electronic health records (EHR) due to regulatory constraints on nurse-patient interactions. We introduce TriageSim, a simulation framework for generating persona-conditioned triage conversations from structured records. TriageSim enables multi-turn nurse-patient interactions with explicit control over disfluency and decision behaviour, producing a corpus of ~800 synthetic transcripts and corresponding audio. We use a combination of automated analysis for linguistic, behavioural and acoustic fidelity alongside manual evaluation for medical fidelity using a random subset of 50 conversations. The utility of the generated corpus is examined via conversational triage classification. We observe modest agreement for acuity levels across three modalities: generated synthetic text, ASR transcripts, and direct audio inputs. We provide the code for TriageSim at https://github.com/dipankarsrirag/triage-sim.git.

arXiv

A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models

Xiulin Yang, Arianna Bisazza, Nathan Schneider, Ethan Gotlieb Wilcox

Several recent contributions have evaluated the Poverty of the Stimulus Hypothesis (PoSH) using Artificial Neural Networks (ANNs). The results suggest that ANN-based language models can acquire certain structure-dependent generalizations from limited input without structural inductive biases of the type traditionally hypothesized by linguists. However, existing studies have largely focused on individual phenomena and adopted different evaluation protocols, leaving it unclear whether previous findings generalize across phenomena and learning conditions. We introduce \poshbench, a unified benchmark covering four canonical PoS phenomena. Training Transformer, LSTM, and n-gram models, we find that ANN-based models can achieve above-chance generalization from surprisingly limited input (10M words), but they show less efficient learning than children as input scale grows. Moreover, cognitively motivated inductive biases substantially improve broad syntactic competence but do not consistently translate to PoS-relevant generalization. Our findings provide systematic evidence challenging the claim that innate syntax is the only possible route to generalization, while suggesting that human-like learning efficiency requires inductive biases beyond those implemented here.

arXiv

Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding

Yuling Shi, Chaoxiang Xie, Zhensu Sun, Yeheng Chen, Chenxu Zhang, Longfei Yun, Chengcheng Wan, Hongyu Zhang, David Lo, Xiaodong Gu

Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based paradigm that treats source code as a linear sequence of tokens, which leads to a linear increase in context length and associated computational costs. The rapid advancement of Multimodal LLMs (MLLMs) introduces an opportunity to optimize efficiency by representing source code as rendered images. Unlike text, which is difficult to compress without losing semantic meaning, the image modality is inherently suitable for compression. By adjusting resolution, images can be scaled to a fraction of their original token cost while remaining recognizable to vision-capable models. To explore the feasibility of this approach, we conduct the first systematic study on the effectiveness of MLLMs for code understanding. Our experiments reveal that: (1) MLLMs can effectively understand code with substantial token reduction, achieving up to 8x compression; (2) MLLMs can effectively leverage visual cues such as syntax highlighting, improving code completion performance under 4x compression; and (3) Code-understanding tasks like clone detection exhibit exceptional resilience to visual compression, with some compression ratios even slightly outperforming raw text inputs. Our findings highlight both the potential and current limitations of MLLMs in code understanding, which points out a shift toward image-modality code representation as a pathway to more efficient inference.

arXiv

Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention

Junbo Zhang, Ran Chen, Qianli Zhou, Xinyang Deng, Wen Jiang

Large language models (LLMs) demonstrate powerful capabilities across various natural language processing tasks,yet their inherent safety vulnerabilities undermine the reliable application of LLMs in real-world scenarios. To enhance LLM safety, various jailbreak defense methods have been proposed to guard against harmful outputs. However, improvements in model safety often come at the cost of severe over-refusal, failing to strike a good balance between safety and usability. This phenomenon is a critical reliability degradation issue in LLM intelligent systems, failing to strike a good balance between safety defense effectiveness and system usability reliability. In this paper, we first analyze the causes of over-refusal from a representation perspective, revealing that LLMs are unable to effectively distinguish between over-refusal samples and malicious samples. Based on this, we propose to mitigate overrefusal by intervening in the safety representation space of LLMs. Our method incorporates two core strategies: (1) OverlapAware Loss Weighting, which determines the erasure weight for malicious samples by quantifying their similarity to overrefusal samples in the representation space, and (2) ContextAware Augmentation, which supplements the necessary context for rejection decisions by adding harmful prefixes before rejection responses. Experiments demonstrate that our method achieves a better trade-off between mitigating over-refusal and maintaining safety, compared with existing approaches. This paper also aims to encourage researchers to consider the reliability of defending methods against jailbreak attacks from both the perspectives of safety and over-refusal.

arXiv

Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models

Harm Lameris, Shree Harsha Bokkahalli Satish, Joakim Gustafson, Éva Székely

Recent advances in Speech Foundation Models (SFMs) enable direct processing of raw audio, allowing models to respond to subtle paralinguistic variation. However, how these models interpret non-lexical cues remains largely unstudied. We introduce VQ-Bench, a controlled evaluation suite featuring a parallel dataset of synthesized modal, breathy, creaky, and end-creak phonation types. We evaluate SFM sensitivity through open-ended generation across four ecologically valid domains, alongside speech emotion recognition. Our results reveal performance gaps: while a leading commercial API failed basic biometric sanity checks, other models exhibited systematic shifts in agency, empathy, and leadership based on phonation. Our findings also highlight gender asymmetries in salary and leadership endorsements, demonstrating that SFMs may mirror or amplify human social biases. This work establishes a reproducible framework for ensuring responsible paralinguistic interpretation in speech-based AI.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →