论文检索

Applications · Language, Speech and Dialog

Junhong Lin, Xinyue Zeng, Jie Zhu, Song Wang, Julian Shun, Jun Wu, Dawei Zhou

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate verbose and tangential reasoning traces even for simple queries. Recent work has tried to mitigate this by enforcing fixed token budgets, however, this can lead to underthinking, especially on harder problems. Through empirical analysis, we identify that this inefficiency often stems from unclear problem-solving strategies. To formalize this, we develop a theoretical model, BAM (Budget Allocation Model), which models reasoning as a sequence of sub-questions with varying uncertainty, and introduce the E3 metric to capture the trade-off between correctness and computation efficiency. Building on theoretical results from BAM, we propose Plan-and-Budget, a model-agnostic, test-time framework that decomposes complex queries into sub-questions and allocates token budgets based on estimated complexity using adaptive scheduling. Plan-and-Budget improves reasoning efficiency across a range of tasks and models, achieving up to 70% accuracy gains, 39% token reduction, and 193.8% improvement in E3. Notably, it improves the efficiency of a smaller model (DS-Qwen-32B) to match the efficiency of a larger model (DS-LLaMA-70B), demonstrating Plan-and-Budget’s ability to close performance gaps without retraining. Our code is available at https://github.com/junhongmit/P-and-B.

Applications · Language, Speech and Dialog

Yi-Jen Shih, Desh Raj, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer

Recent advances in speech large language models (speech LLMs) have enabled seamless spoken interactions, but these systems still struggle with complex reasoning tasks. Previously, chain-of-thought (CoT) prompting or fine-tuning has been shown to significantly improve the reasoning abilities of text-based LLMs. In this work, we investigate the effect of CoT fine-tuning for multi-stream speech LLMs, demonstrating that reasoning in text space improves the accuracy of speech LLMs by 2.4x, on average, over a suite of spoken reasoning tasks. Beyond accuracy, the latency of the spoken response is a crucial factor for interacting with voice-based agents. Inspired by the human behavior of "thinking while listening," we propose methods to reduce the additional latency from reasoning by allowing the model to start reasoning before the user query has ended. To achieve this, we introduce an entropy-based metric, "question completeness," which acts as an indicator to guide the model on the optimal time to start reasoning. This method provides greater control over the accuracy-latency trade-off compared with heuristic-based approaches and, under equivalent latency conditions, yields a 4% accuracy gain on ARC-Easy. Finally, we use Direct Preference Optimization (DPO) on preference data created using rejection sampling to push the accuracy-latency pareto frontier further, resulting in a 70% reduction in latency without loss in accuracy.

Applications · Language, Speech and Dialog

Jiachun Li, Shaoping Huang, Zhuoran Jin, Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathematical reasoning. Despite their promise, MLLMs' reasoning abilities across different scenarios in real life remain largely unexplored and lack standardized benchmarks for evaluation. To address this gap, we introduce MMR-Life, a comprehensive benchmark designed to evaluate the diverse multimodal multi-image reasoning capabilities of MLLMs across real-life scenarios. MMR-Life consists of 2,646 multiple-choice questions based on 19,108 images primarily sourced from real-world contexts, comprehensively covering seven reasoning types: abductive, analogical, causal, deductive, inductive, spatial, and temporal. Unlike existing reasoning benchmarks, MMR-Life does not rely on domain-specific expertise but instead requires models to integrate information across multiple images and apply diverse reasoning abilities. The evaluation of 37 advanced models highlights the substantial challenge posed by MMR-Life. Even top models like GPT-5 achieve only 58% accuracy and display considerable variance in performance across reasoning types. Moreover, we analyze the reasoning paradigms of existing MLLMs, exploring how factors such as thinking length, reasoning method, and reasoning type affect their performance. In summary, MMR-Life establishes a comprehensive foundation for evaluating, analyzing, and improving the next generation of multimodal reasoning systems.

Applications · Language, Speech and Dialog

Xinran Zhao, Aakanksha Naik, Jay DeYoung, Joseph Chee Chang, Jena Hwang, Sherry Wu, Varsha Kishore

Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes and intents that guide authors in crafting these documents. We hypothesize that enhancing a model's intent awareness can significantly improve the quality of generated long-form reports. We develop and employ structured, tag-based schemes to better elicit underlying implicit intents to write or cite. We demonstrate that these extracted intents enhance both zero-shot generation capabilities in LLMs and enable the creation of high-quality synthetic data for fine-tuning smaller models. Our experiments reveal improved performance across various challenging scientific report generation tasks, with an average improvement of +2.9 and +12.3 absolute points for large and small models over baselines, respectively. Furthermore, our analysis illuminates how intent awareness enhances model citation usage and substantially improves report readability.

Applications · Language, Speech and Dialog

Penny Chong, Harshavardhan Abichandani, Jiyuan SHEN, Atin Ghosh, Min Moe, Yifan Mai, Daniel Dahlmeier

Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation framework. Prior works each employ their own methods to determine task success, such as database lookups, regex match, etc., adding complexity to the development of a unified agent evaluation approach. Moreover, they do not systematically account for the user’s role nor expertise in the interaction, providing incomplete insights into the agent’s performance. We argue that effective agent evaluation goes beyond correctness alone, incorporating conversation quality, efficiency and systematic diagnosis of agent errors. To address this, we introduce the TED framework (Talk, Evaluate, Diagnose). (1) Talk: We leverage reusable, generic expert and non-expert user persona templates for user-agent interaction. (2) Evaluate: We adapt existing datasets by representing subgoals—such as tool signatures, and responses—as natural language grading notes, evaluated automatically with LLM-as-a-judge. We propose new metrics that capture both turn efficiency and intermediate progress of the agent complementing the user-aware setup. (3) Diagnose: We introduce an automated error analysis tool that analyzes the inconsistencies of the judge and agents, uncovering common errors, and providing actionable feedback for agent improvement. We show that our TED framework reveals new insights regarding agent performance across models and user expertise levels. We also demonstrate potential gains in agent performance with peaks of 8-10% on our proposed metrics after incorporating the identified error remedies into the agent’s design.

Applications · Language, Speech and Dialog

Peter Baile Chen, Weiyue Li, Dan Roth, Mike Cafarella, Samuel Madden, Jacob Andreas

AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system that maps tasks to the appropriate strategies is crucial. Most prior methods build the routing framework by training a *single* model across *all* strategies, which demands full retraining whenever new strategies appear and leads to high overhead. Attempts at such continual routing, however, often face difficulties with generalization. Prior models also typically use a *single* input representation, limiting their ability to capture the full complexity of the routing problem and leading to sub-optimal routing decisions. To address these gaps, we propose CONCUR, a **con**tinual routing framework that supports both **c**onstrained and **u**nconstrained **r**outing (i.e., routing with or without a budget). Our *modular* design trains a separate predictor model for each strategy, enabling seamless incorporation of new strategies with low additional training cost. Our predictors also leverage *multiple* representations of both tasks and computation strategies to better capture overall problem complexity. Experiments on both in-distribution and out-of-distribution, knowledge- and reasoning-intensive tasks show that our method outperforms the best single strategy and strong existing routing techniques with higher end-to-end accuracy and lower inference cost in both continual and non-continual settings, while also reducing training cost in the continual setting.

Applications · Language, Speech and Dialog

Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty

Deep research---producing comprehensive, citation-backed reports by searching across hundreds of live websites---marks an important frontier for agentic systems. To rigorously evaluate this ability, three principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, and (3) unambiguous, ensuring consistent interpretation across users. Existing benchmarks fall short of these principles, often focusing on narrow domains or posing ambiguous questions that hinder fair comparison. Guided by these principles, we introduce LiveResearchBench, a benchmark of 100 expert-curated tasks spanning daily life, enterprise, and academia, each requiring extensive, dynamic, real-time web search and synthesis. Built with over 1,500 hours of human labor, LiveResearchBench provides a rigorous basis for systematic evaluation. To evaluate citation-grounded long-form reports, we present DeepEval, a comprehensive suite covering both content- and report-level quality: checklists for coverage and presentation, rubric-tree assessments of citation accuracy and traceability, and metrics for consistency and depth of analysis. Using LiveResearchBench and DeepEval, we conduct a comprehensive evaluation of frontier deep research systems, including single-agent web search, single-agent deep research, and multi-agent systems. Our analysis reveals current strengths, recurring failure modes, and key system components needed to advance reliable, insightful deep research. Our code is available at: https://github.com/SalesforceAIResearch/LiveResearchBench.

Applications · Language, Speech and Dialog

Jiachun Li, Pengfei Cao, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time reward model (RM)-based reasoning as a critical yet overlooked avenue. In this paper, we conduct a systematic analysis of RM behavior across downstream reasoning tasks, revealing three key limitations: (1) RM can impair performance on simple questions, (2) its discriminative ability declines with increased sampling, and (3) high search diversity undermines RM performance. To address these issues, we propose CRISP (Clustered Reward Integration with Stepwise Prefixing), a novel inference-time algorithm that clusters generated reasoning paths by final answers, aggregates reward signals at the cluster level, and adaptively updates prefix prompts to guide generation. Experimental results demonstrate that CRISP significantly enhances LLM reasoning performance, achieving up to 5% accuracy improvement over other RM-based inference methods and an average of 10% gain over advanced reasoning models.

Applications · Language, Speech and Dialog

Taeyoon Kwon, Dongwook Choi, Hyojun Kim, Sunghwan Kim, Seungjun Moon, Beong-woo Kwak, Kuan-Hao Huang, Jinyoung Yeo

LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these challenges through the lens of agents' memory utilization along two critical dimensions: object semantics (identifying objects based on personal meaning) and user patterns (recalling sequences from behavioral routines). To assess these capabilities, we construct Memento, an end-to-end two-stage evaluation framework comprising single-memory and joint-memory tasks. Our experiments reveal that current agents can recall simple object semantics but struggle to apply sequential user patterns to planning. Through in-depth analysis, we identify two critical bottlenecks: information overload and coordination failures when handling multiple memories. Based on these findings, we explore memory architectural approaches to address these challenges. Given our observation that episodic memory provides both personalized knowledge and in-context learning benefits, we design a hierarchical knowledge graph-based user-profile memory module that separately manages personalized knowledge, achieving substantial improvements on both single and joint-memory tasks.

Applications · Language, Speech and Dialog

Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Yuxuan Wang, Chao Zhang

Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and interruptions. Realizing these capabilities is essential for building models simulating humans. We present ELLSA (End-to-end Listen, Look, Speak and Act), which, to our knowledge, is the first full-duplex, end-to-end model that simultaneously perceives and generates across vision, text, speech, and action within a single architecture, enabling interaction patterns previously out of reach, yielding more natural, human-like behaviors. At its core is a novel SA-MoE architecture (Self-Attention Mixture-of-Experts) that routes each modality to specialized experts and fuses them through a unified attention backbone. This provides a generalizable solution for joint multimodal perception and concurrent generation, leveraging strong pre-trained components while enabling efficient modality integration and mitigating modality interference. On speech-interaction and robot-manipulation benchmarks, ELLSA matches modality-specific baselines, while uniquely supporting advanced multimodal and full-duplex behaviors such as dialogue and action turn-taking, defective instruction rejection, speaking-while-acting, context-grounded visual question answering, and action barge-ins. We contend that ELLSA represents a step toward more natural and general interactive intelligence, contributing to the broader pursuit of artificial general intelligence. A demonstration is available at https://anonymous.4open.science/r/LLSA-E821.

Applications · Language, Speech and Dialog

Shengjie Gong, Wenjie Peng, Hongyuan Chen, Gangyu Zhang, Yunqing Hu, Huiyuan Zhang, Shuangping Huang, Tianshui Chen

Text-to-CAD code generation is a long-horizon task, requiring the translation of instructions into a long sequence of interdependent operations. This process is exceptionally fragile, as minor early errors can propagate through the sequence and ultimately invalidate an entire complex assembly. Existing methods typically decode instructions directly into executable code (e.g., bpy) without an explicit representation of assembly hierarchy or geometric constraints. This flat decoding strategy vastly expands the search space, amplifying local errors and leading to cascading failures in contextual operations. We address this gap by learning an intermediate representation: a hierarchical and geometry-aware graph. The graph represents an assembly-based decomposition, with multi-level nodes modeling the product's parts and components, and edges defining the explicit geometric constraints between them. Rather than mapping text directly to code, our graph paradigm first predicts high-level structure and constraints, then conditions the sequencing of operations and program generation, thereby narrowing the search space and improving both geometric fidelity and constraint satisfaction. Furthermore, we introduce a structure-aware progressive curriculum learning mechanism to enhance the model's ability to generate sophisticated decomposition graphs, allowing it to handle more complex assemblies. The mechanism constructs graded tasks via controlled edits to object structure, probes the model’s capability boundary, and synthesizes boundary examples for subsequent training rounds. We also introduce a 12K-instruction dataset annotated with instructions, geometric decomposition graphs, action sequences, and bpy code, together with metrics for node- and hierarchy-level graph accuracy and a measure of constraint satisfaction. Extensive experiments show that our approach outperforms existing methods in terms of both geometric fidelity and accurate fulfillment of geometric constraints.

Applications · Language, Speech and Dialog

Peter Baile Chen, Yi Zhang, Dan Roth, Samuel Madden, Jacob Andreas, Mike Cafarella

While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts often fail to retain reasoning from previous tasks and apply it to future contexts. We introduce **L**og-**A**ugmented **G**eneration (LAG), a novel framework that *directly reuses* prior computation and reasoning from past logs at test time, enabling models to learn from previous tasks to perform better on new, unseen challenges, without sacrificing efficiency or scalability. Our approach represents task logs as key-value (KV) caches that encode the reasoning context of prior tasks, while storing KV values for only a selected subset of tokens. When a new task arises, LAG retrieves KV values from relevant logs to augment generation. Unlike reflection-based memory mechanisms, which require additional extraction or distillation steps, LAG reuses prior reasoning verbatim. Moreover, it extends beyond existing KV caching techniques, primarily designed for efficiency, by explicitly improving accuracy through log reuse. Experiments on knowledge- and reasoning-intensive datasets demonstrate that our method significantly outperforms standard agentic systems without log utilization, as well as existing approaches based on reflection and KV cache techniques.

Applications · Language, Speech and Dialog

Chenyu Wang, Paria Rashidinejad, Andy (DiJia) Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Shen, Feiyu Chen, Tommi Jaakkola 等

Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, aligning dLLMs with human preferences or task-specific rewards via reinforcement learning (RL) is challenging because their intractable log-likelihood precludes the direct application of standard policy gradient methods. While prior work uses surrogates like the evidence lower bound (ELBO), these one-sided approximations can introduce significant policy gradient bias. To address this, we propose the Sandwiched Policy Gradient (SPG) that leverages both an upper and a lower bound of the true log-likelihood. Experiments show that SPG significantly outperforms baselines based on ELBO or one-step estimation. Specifically, SPG improves the accuracy over state-of-the-art RL methods for dLLMs by 3.6% on GSM8K, 2.6% on MATH500, 18.4% on Countdown, and 27.0% on Sudoku.

Applications · Language, Speech and Dialog

Vésteinn Snæbjarnarson, Samuel Kiegeland, Tianyu Liu, Reda Boumasmoud, Ryan Cotterell, Tim Vieira

Modern language models define distributions over strings, but downstream tasks often require different output formats. For instance, a model that generates byte-pair strings does not directly produce word-level predictions, and a DNA model does not directly produce amino-acid sequences. In such cases, a deterministic string-to-string transformation can convert the model's output to the desired form. This is a familiar pattern in probability theory: applying a function $f$ to a random variable $X\sim p$ yields a transformed random variable $f(X)$ with an induced distribution. While such transformations are occasionally used in language modeling, prior work does not treat them as yielding new, fully functional language models. We formalize this perspective and introduce a general framework for language models derived from deterministic string-to-string transformations. We focus on transformations representable as finite-state transducers---a commonly used state-machine abstraction for efficient string-to-string mappings. We develop algorithms that compose a language model with an FST to *marginalize* over source strings mapping to a given target, propagating probabilities through the transducer without altering model parameters and enabling *conditioning* on transformed outputs. We present an exact algorithm, an efficient approximation, and a theoretical analysis. We conduct experiments in three domains: converting language models from tokens to bytes, from tokens to words, and from DNA to amino acids. These experiments demonstrate inference-time adaptation of pretrained language models to match application-specific output requirements.

Applications · Language, Speech and Dialog

Tom Kempton, Julia Rozanova, Parameswaran Kamalaruban, Maeve Madigan, Karolina Wresilo, Yoann Launay, David Sutton, Stuart Burrell

Large Language Models (LLMs) are a powerful tool for statistical text analysis, with derived sequences of next-token probability distributions offering a wealth of information. Extracting this signal typically relies on metrics such as perplexity, which do not adequately account for context; how one should interpret a given next-token probability is dependent on the number of reasonable choices encoded by the shape of the conditional distribution. In this work, we present DMAP, a mathematically grounded method that maps a text, via a language model, to a set of samples in the unit interval that jointly encode rank and probability information. This representation enables efficient, model-agnostic analysis and supports a range of applications. We illustrate its utility through three case studies: (i) validation of generation parameters to ensure data integrity, (ii) examining the role of probability curvature in machine-generated text detection, and (iii) a forensic analysis revealing statistical fingerprints left in downstream models that have been subject to post-training on synthetic data. Our results demonstrate that DMAP offers a unified statistical view of text that is simple to compute on consumer hardware, widely applicable, and provides a foundation for further research into text analysis with LLMs.

Applications · Language, Speech and Dialog

Yilei Chen, Souradip Chakraborty, Lorenz Wolf, Ioannis Paschalidis, Aldo Pacchiano

Reinforcement learning has emerged as a popular method for post-training large language models (LLMs). While improving the model's performance on downstream tasks, it often reduces the model's output diversity, leading to narrow, canonical responses. Existing methods to enhance diversity are limited, either by operating at inference time or by focusing on lexical differences. We propose a novel training method named DQO (Diversity Quality Optimization) based on determinantal point processes (DPPs) to jointly optimize LLMs for quality and semantic diversity. Our approach samples and embeds a group of responses for each prompt, then uses the determinant of a kernel-based similarity matrix to measure diversity as the volume spanned by the embeddings of these responses. Experiments across instruction-following, summarization, story generation, and reasoning tasks demonstrate that our method substantially improves semantic diversity without sacrificing model quality.

Applications · Language, Speech and Dialog

Min-Sang Baek, Gyeong-Su Kim, Donghyun Kim, Joon-Hyuk Chang

Sound source localization (SSL) is a fundamental task in spatial audio understanding, yet most deep neural network-based methods are constrained by fixed array geometries and predefined directional grids, limiting generalizability and scalability. To address these issues, we propose _audio-geometry-grid representation learning_ (AGG-RL), a novel framework that jointly learns audio-geometry and grid representations in a shared latent space, enabling both geometry-invariant and grid-flexible SSL. Moreover, to enhance generalizability and interpretability, we introduce two physics-informed components: a _learnable non-uniform discrete Fourier transform_ (LNuDFT), which optimizes the dense allocation of frequency bins in a non-uniform manner to emphasize informative phase regions, and a _relative microphone positional encoding_ (rMPE), which encodes relative microphone coordinates in accordance with the nature of inter-channel time differences. Experiments on synthetic and real datasets demonstrate that AGG-RL achieves superior performance, particularly under unseen conditions. The results highlight the potential of representation learning with physics-informed design towards a universal solution for spatial acoustic scene understanding across diverse scenarios.

Applications · Language, Speech and Dialog

Jiliang Ni, Jiachen Pu, Zhongyi Yang, Jingfeng Luo, Conggang Hu

The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However, existing paradigms are often plagued by overfitting, training instability, ineffective binary rewards for multi-solution tasks, and the difficulty of synergizing techniques. We introduce STAR: Similarity-guided Teacher-Assisted Refinement, a novel holistic framework that effectively transfers LLMs' capabilities to super-tiny models. STAR consists of two core technical innovations: (1) Constrained Knowledge Distillation (CKD), a training objective that augments top-k forward KL divergence to suppress confidently incorrect predictions, ensuring training stability while preserving exploration capacity for downstream RL. STAR holistically synergizes these strategies within a cohesive training curriculum, enabling super-tiny models to achieve exceptional performance on complex function calling tasks; (2) Similarity-guided RL (Sim-RL), a RL mechanism that introduces a fine-grained, similarity-based reward. This provides a robust, continuous, and rich signal for better policy optimization by evaluating the similarity between generated outputs and the ground truth. Extensive experiments on challenging and renowned benchmarks demonstrate the effectiveness of our method. Our STAR models establish SOTA in their size classes, significantly outperforming baselines. Remarkably, our 0.6B STAR model achieves the best performance among all open models under 1B, surpassing even several well-known open models at a larger scale. STAR demonstrates a training framework that distills capabilities of LLMs into super-tiny models, paving the way for powerful, accessible, and efficient AI agents.

Applications · Language, Speech and Dialog

Yueqi Song, Ketan Ramaneti, Zaid Sheikh, Ziru Chen, Boyu Gou, Tianbao Xie, Yiheng Xu, Danyang Zhang, Apurva Gandhi, Fan Yang 等

Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying data sources, but that a large variety of data is fragmented across heterogeneous formats, tools, and interfaces. To this end, we introduce the Agent Data Protocol (ADP), a light-weight representation language that serves as an "interlingua" between agent datasets in diverse formats and unified agent training pipelines downstream. The design of ADP is expressive enough to capture a large variety of tasks, including API/tool use, browsing, coding, software engineering, and general agentic workflows, while remaining simple to parse and train on without engineering at a per-dataset level. In experiments, we unified a broad collection of 13 existing agent training datasets into ADP format, and converted the standardized ADP data into training-ready formats for multiple agent frameworks. We performed supervised finetuning on the unified data, and demonstrated an average performance gain of $\sim$20\% over corresponding base models, and delivers state-of-the-art or near-SOTA performance on standard coding, browsing, tool use, and research benchmarks, without domain-specific tuning. All code and data are released publicly, in the hope that ADP could help lower the barrier to standardized, scalable, and reproducible agent training.

Applications · Language, Speech and Dialog

Arkadiy Saakyan, Najoung Kim, Smaranda Muresan, Tuhin Chakrabarty

$N$-gram novelty is widely used to evaluate language models' ability to generate text outside of their training data. More recently, it has also been adopted as a metric for measuring textual creativity. However, theoretical work on creativity suggests that this approach may be inadequate, as it does not account for creativity's dual nature: novelty (how original the text is) and appropriateness (how sensical and pragmatic it is). We investigate the relationship between this notion of creativity and $n$-gram novelty through 8,618 expert writer annotations of novelty, pragmaticality, and sensicality via \emph{close reading} of human- and AI-generated text. We find that while $n$-gram novelty is positively associated with expert writer-judged creativity, approximately 91% of top-quartile $n$-gram novel expressions are not judged as creative, cautioning against relying on $n$-gram novelty alone. Furthermore, unlike in human-written text, higher $n$-gram novelty in open-source LLMs correlates with lower pragmaticality. In an exploratory study with frontier closed-source models, we additionally confirm that they are less likely to produce creative expressions than humans. Using our dataset, we test whether zero-shot, few-shot, and finetuned models are able to identify expressions perceived as novel by experts (a positive aspect of writing) or non-pragmatic (a negative aspect). Overall, frontier LLMs exhibit performance much higher than random but leave room for improvement, especially struggling to identify non-pragmatic expressions. We further find that LLM-as-a-Judge novelty ratings align with expert writer preferences in an out-of-distribution dataset, more so than an n-gram based metric.