Rewriting inputs to improve frozen downstream models has become a common strategy in modern NLP pipelines. Prior work on incremental dialogue discourse parsing (DDP) shows that supervised clarification models can rewrite fragmentary or underspecified utterances—such as resolving ellipsis or references—to improve parsing accuracy. In this work, we revisit this idea under realistic deployment conditions, where no clarification supervision is available and the clarifier must rely on zero-shot prompting or feedback from a frozen parser. Across three Segmented Discourse Representation Theory (SDRT) datasets and multiple parsers, we find that last-utterance clarification is far less reliable than suggested by supervised settings. Parser-agnostic rewriting often introduces more regressions than repairs, as edits that enable fixes also disrupt discourse cues relied upon by the parser. A best-of-8 rewriting analysis further reveals a practical ceiling: a large fraction of errors are not repairable through input rewriting alone. A parser-aware clarifier trained with GRPO reduces regressions by up to 37% by learning conservative abstention, yet still fails to produce selectivity-aware clarifications that consistently improve parsing. Together, these findings recast clarification as a selective intervention problem. We identify rewritability prediction—deciding whether an utterance is repairable before intervention—as the key missing capability for input-side optimization of frozen discourse parsers, and a critical direction for improving agentic pipelines more broadly.[Data and code are available at https://github.com/ounlp/Clarification-for-DDP.]

Human tutoring interventions play a crucial role in supporting student learning, improving academic performance, and promoting personal growth. This paper focuses on analyzing mathematics tutoring discourse using talk moves—a framework of dialogue acts grounded in Accountable Talk theory. However, scaling the collection, annotation, and analysis of extensive tutoring dialogues to develop machine learning models is a challenging and resource-intensive task. To address this, we present SAGA22, a compact dataset, and explore various modeling strategies, including dialogue context, speaker information, pretraining datasets, and further fine-tuning. By leveraging existing datasets and models designed for classroom teaching, our results demonstrate that supplementary pretraining on classroom data enhances model performance in tutoring settings, particularly when incorporating longer context and speaker information. Additionally, we conduct extensive ablation studies to underscore the challenges in talk move modeling.

We investigate whether large language models encode latent knowledge of frame semantics, focusing on frame identification, a core challenge in frame semantic parsing that involves selecting the appropriate semantic frame for a target word in context.Using the FrameNet lexical resource, we evaluate models under prompt-based inference and observe that they can perform frame identification effectively even without explicit supervision.To assess the impact of task-specific training, we fine-tune the model on FrameNet data, which substantially improves in-domain accuracy while generalizing well to out-of-domain benchmarks.Further analysis shows that the models can generate semantically coherent frame definitions, highlighting the model's internalized understanding of frame semantics.

Deep learning approaches have provided state-of-the-art performance in many applications by relying on large and overparameterized neural networks. However, such networks are very brittle and are difficult to deploy on resource-limited platforms. Model pruning, i.e., reducing the size of the network, is a widely adopted strategy that can lead to a more robust and compact model. Many heuristics exist for model pruning, but our understanding of the pruning process remains limited due to the black-box nature of a neural network model. Empirical studies show that some heuristics improve performance whereas others can make models more brittle. This work aims to shed light on how different pruning methods alter the network's internal feature representation and the corresponding impact on model performance. To facilitate a comprehensive comparison and characterization of the high-dimensional model feature space, we introduce a visual geometric analysis of feature representations. We evaluated a set of critical geometric concepts decomposed from the commonly adopted classification loss and used them to design a visualization system to compare and highlight the impact of pruning on model performance and feature representation. The proposed tool provides an environment for an in-depth comparison of pruning methods and a comprehensive understanding of how the model responds to common data corruption. By leveraging the proposed visualization, machine learning researchers can reveal the similarities between pruning methods and redundancy in robustness evaluation benchmarks, obtain geometric insights about the differences between pruned models that achieve superior robustness performance, and identify samples that are robust or fragile to model pruning and common data corruption.

In mathematics tutoring, using appropriate instructional discursive strategies, called "talk moves'', is critical to support student learning. Training tutors in the appropriate use of talk moves is a key component of tutor development programs. However, tutor development at scale is a challenge. Recent research has shown that automatic talk moves classification of tutorial discourse can facilitate large-scale delivery of personalized talk moves feedback. In this paper, we build on this work and share our current progress using large language models to classify talk moves in transcripts of tutoring sessions. We report classification results from fine-tuned models, prompt optimization, and supervised embedding vectors classification. The fine-tuned strategy performed best, yielding better performance (.87 macro and .93 weighted f1 score in predicting expert labels) than the current state-of-the-art RoBERTa model. We discuss trade-offs across methods and models.

In collaborative learning environments, effective intelligent learning systems need to accurately analyze and understand the collaborative discourse between learners (i.e., group modeling) to provide adaptive support. We investigate how automatic speech recognition (ASR) errors influence discourse models of small group collaboration in noisy real-world classrooms. Our dataset consisted of 30 students recorded by consumer off-the-shelf microphones (Yeti Blue) while engaging in dyadic- and triadic- collaborative learning in a multi-day STEM curriculum unit. We found that two state-of-the-art ASR systems (Google Speech and OpenAI Whisper) yielded very high word error rates (0.822, 0.847) but very different profiles of error with Google being more conservative, rejecting 38% of utterances instead of 12% for Whisper. Next, we examined how these ASR errors influenced down-stream small group modeling based on pre-trained large language models for three tasks: Abstract Meaning Representation parsing (AMRParsing), on-task/off-task detection (OnTask), and Accountable Productive Talk prediction (TalkMove). As expected, models trained on clean human transcripts yielded degraded performance on all three tasks, measured by the transfer ratio (TR). However, the TR of the specific sentence-level AMRParsing task (.39 - .62) was much lower than that of the abstract discourse-level OnTask (.63- .94) and TalkMove tasks (.64-.72). Furthermore, different training strategies that incorporated ASR transcripts alone or as augmentations of human transcripts increased accuracy for the discourse-level tasks (OnTask and TalkMove) but not AMRParsing. Simulation experiments suggested that the models were tolerant of missing utterances in the dialog context, and that jointly improving ASR accuracy on important word classes (e.g., verbs and nouns) can improve performance across all tasks. Overall, our results provide insights into how different types of NLP-based tasks might be tolerant of ASR errors under extremely noisy conditions and provide suggestions for how to improve accuracy in small group modeling settings for a more equitable, engaging, and adaptive collaborative learning environment.

Frame-based state representation is widely used in modern task-oriented dialog systems to model user intentions and slot values.However, a fixed design of domain ontology makes it difficult to extend to new services and APIs.Recent work proposed to use natural language descriptions to define the domain ontology instead of tag names for each intent or slot, thus offering a dynamic set of schema.In this paper, we conduct in-depth comparative studies to understand the use of natural language description for schema in dialog state tracking.Our discussion mainly covers three aspects: encoder architectures, impact of supplementary training, and effective schema description styles.We introduce a set of newly designed bench-marking descriptions and reveal the model robustness on both homogeneous and heterogeneous description styles in training and evaluation.

Smart databases are adopting artificial intelligence (AI) technologies to achieve instance optimality , and in the future, databases will come with prepackaged AI models within their core components. The reason is that every database runs on different workloads, demands specific resources, and settings to achieve optimal performance. It prompts the necessity to understand workloads running in the system along with their features comprehensively, which we dub as workload characterization. To address this workload characterization problem, we propose our query plan encoders that learn essential features and their correlations from query plans. Our pretrained encoders captures the structural and the computational performance of queries independently. We show that our pretrained encoders are adaptable to workloads that expedites the transfer learning process. We performed independent assessments of structural encoder and performance encoders with multiple downstream tasks. For the overall evaluation of our query plan encoders, we architect two downstream tasks (i) query latency prediction and (ii) query classification. These tasks show the importance of feature-based workload characterization. We also performed extensive experiments on individual encoders to verify the effectiveness of representation learning, and domain adaptability.

Automatically analyzing dialogue can help understand and guide behavior in domains such as counseling, where interactions are largely mediated by conversation.In this paper, we study modeling behavioral codes used to asses a psychotherapy treatment style called Motivational Interviewing (MI), which is effective for addressing substance abuse and related problems.Specifically, we address the problem of providing real-time guidance to therapists with a dialogue observer that (1) categorizes therapist and client MI behavioral codes and, (2) forecasts codes for upcoming utterances to help guide the conversation and potentially alert the therapist.For both tasks, we define neural network models that build upon recent successes in dialogue modeling.Our experiments demonstrate that our models can outperform several baselines for both tasks.We also report the results of a careful analysis that reveals the impact of the various network design tradeoffs for modeling therapy dialogue.Code Count Description Examples Client Behavioral Codes FN 47715 Follow/ Neutral: unrelated to changing or sustaining behavior."You know, I didn't smoke for a while.""I have smoked for forty years now."CT 5099 Utterances about changing unhealthy behavior."I want to stop smoking."ST 4378 Utterances about sustaining unhealthy behavior."I really don't think I smoke too much."Therapist Behavioral Codes FA 17468 Facilitate conversation "Mm Hmm.", "OK.","Tell me more."GI 15271 Give information or feedback."I'm Steve.","Yes, alcohol is a depressant."RES 6246 Simple reflection about the clients most recent utterance.C: "I didn't smoke last week" T: "Cool, you avoided smoking last week."REC 4651 Complex reflection based on a client's history or the broader conversation.C: "I didn't smoke last week."T: "You mean things begin to change".QUC 5218 Closed question "Did you smoke this week?"QUO 4509 Open question "Tell me more about your week."MIA 3869 Other MI adherent,e.g., affirmation, advising with permission, etc. "You've accomplished a difficult task." "Is it OK if I suggested something?"MIN 1019 MI non-adherent, e.g., confrontation, advising without permission, etc. "You hurt the baby's health for cigarettes?" "You ask them not to drink at your house."

Rhetoric is a vital element in modern poetry, and plays an essential role in improving its aesthetics.However, to date, it has not been considered in research on automatic poetry generation.In this paper, we propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation.Our model relies on a continuous latent variable as a rhetoric controller to capture various rhetorical patterns in an encoder, and then incorporates rhetoricbased mixtures while generating modern Chinese poetry.For metaphor and personification, an automated evaluation shows that our model outperforms state-of-the-art baselines by a substantial margin, while a human evaluation shows that our model generates better poems than baseline methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics.

Demands for highly scalable parallel data processing platforms is raising due to an explosion in the number of massive-scale data intensive applications both in industry and in sciences. Performing statistical computing over huge data repositories poses a significant challenge to existing statistical software and computational infrastructure. After analyzing various open source computational infrastructures and their programming paradigm APIs, the results have shown that most of them are JVM based, and their APIs are given as Java interfaces or abstract classes. This paper proposes a generic framework JR Bridge, which can integrate R and JVM-based computational infrastructures by generating Java APIs code wrapper around the native R code automatically and handling type conversion. Using this framework, we build a distributed statistical computing environment by integrating R with Hadoop. With the Hadoop Distributed File System plug in, it brings a way to store and access datasets with millions of objects. With MapReduce plug in, it brings a natural environment to code MapReduce algorithms in R. The experiment result shows JR Bridge scales linearly with the size of the datasets and thus provides a scalable solution for large-scale statistical computing in R.