Computation and Language
S-DiverSe: Spanish Diverse Speech
Fernando López, Fernando Ibañez, Ana Martínez et al. (+4 more)
Automatic
speech recognition (ASR) has advanced remarkably for standard
speech, yet
speech affected by neurological conditions remains a challenge. We present S-DiverSe (Spanish Diverse
Speech), a corpus of 3.2 hours of in-the-wild Spanish
speech from 22 speakers with amyotrophic lateral sclerosis, Parkinson's disease, and stroke. The
dataset contains 444 manually transcribed audio segments with metadata on speaker sex, disease type, and intelligibility. S-DiverSe is designed to support ASR evaluation and development for neurologically affected Spanish
speech. We describe the
dataset, analyze its composition, and report baseline ASR results alongside initial adaptation experiments. Our findings reveal that heuristic text post-processing is more robust than fine-tuning for out-of-domain neurological Spanish
speech. This underscores the need for dedicated in-the-wild Spanish
benchmarks.
Read the full abstract ▾
All authors Fernando López, Fernando Ibañez, Ana Martínez, Iván Alonso, Pablo Gómez, Santosh Kesiraju, Jordi Luque
Computation and Language
KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment
Jinkyeong Choi, Chaebin Jeong and Donghyeon Park
Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates. We formalize this as the Resolution Mismatch Problem and propose KARMA, which enumerates schema-constrained paths over domain knowledge graphs and verbalizes them into slot-aligned contrastive candidates. Slot-Parallel
Alignment (SPA) then applies a decoupled slot-level objective to route preference supervision to discriminative entity-slots, with slot-aware masked
attention serving as an optional packed-evaluation implementation. Across biomedical, computer-science, and chemistry
benchmarks, KARMA outperforms base LLM and same-data SFT baselines, and compares favorably with sequence- and
token-level preference methods.
Read the full abstract ▾
Computation and Language
The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translation
Haohong Lai and Weijia Li
This study examines how
prompt language and translation theory-driven
prompt design influence the quality of Spanish-Chinese journalistic translations generated by GPT-5.2. A parallel corpus of four editorials from El Pais was translated under 48 experimental conditions (4
prompt types, 3
prompt languages, and 4 articles). Translation quality was assessed using BLEU and BERTScore-F1 for automated evaluation, alongside human evaluation based on the Multidimensional Quality Metrics (MQM) framework. Automated metrics identified the baseline
prompt (BASE) as the best-performing condition, whereas human evaluation ranked the brief-oriented
prompt (BRIEF) highest (MQM: 8.66 vs. 7.84), a reversal likely attributable to the single-reference constraint inherent in automated measures. Sub-error type analysis revealed that translation theory-driven
prompts selectively reduced Awkward style errors, while Unidiomatic style errors persisted across conditions.
Prompt language had a negligible impact under both evaluation paradigms. These results indicate that translation theory-driven
prompts can yield measurable quality gains under expert evaluation of journalistic translations, although their pedagogical implications for
language learners remain suggestive and require validation through user-based studies.
Read the full abstract ▾
Computation and Language
Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion
Jiawei Sheng, Taoyu Su, Xixun Lin et al. (+2 more)
Multi-domain knowledge graph completion (MKGC) aims to improve missing triple prediction in a target KG by transferring knowledge from other support KGs. Existing methods typically enforce consistency constraints on equivalent entities across KGs to transfer knowledge, which risks suppressing domain-specific contextual information of entities. This design can also compromise entity representation information from all KG domains, impeding performance improvements, especially in low-resource data scenarios. To address this, we pioneer a generation-based paradigm for MKGC and propose DMKGC, a conditional
diffusion-guided knowledge transfer framework. Our key insight is to treat each KG as a partial view of the entity entire information, and generate informative domain-general entity
embeddings through
diffusion models conditioned on support KGs. Particularly, we first initialize domain-agnostic entity
embeddings as prior entity
embeddings, and then encode them within individual KGs. Afterward, we fuse equivalent entities from support KGs as the conditional
diffusion generation guidance. We leverage the prior entity
embeddings as the proxy generation objective, which ensures this conditional generation to be unbiased towards any conditioned KGs. Simultaneously, we also train the generated
embeddings to be predictive across KGs, thus preserving domain-specific information. Extensive experiments on 14 KGs in 3
benchmarks demonstrate a 4.3% average MRR improvement in tail entity prediction over state-of-the-art methods, with sustained gains in low-resource data settings.
Read the full abstract ▾
All authors Jiawei Sheng, Taoyu Su, Xixun Lin, Xiaodong Li, Tingwen Liu
Computation and Language
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
Ante Wang, Jiaqi Fu, Xuanyi Chen et al. (+4 more)
Thinking has emerged as a critical capability for Large
Language Models (LLMs) tackling complex tasks. However, its reactive nature, where
reasoning is passively triggered only upon receiving a user response, inevitably introduces latency that compromises conversational fluidity. This stands in sharp contrast to human dialogue, where speakers proactively anticipate and plan future content during natural pauses to ensure seamless interaction. To bridge this gap, we propose Proactive Thinking, a framework that empowers models to pre-compute potential response elements during conversational downtime instead of waiting idly for the next input. We then introduce a training-free baseline that can think ahead by anticipating future states, balancing efficiency and quality through speculative continual thinking. To evaluate this approach in practice, we adapt three
benchmarks of varying complexity into time-aware environments that simulate real-time conversational flow. We demonstrate that proactive thinking effectively improves interaction efficiency without compromising performance. Ultimately, this work advocates for a fundamental shift toward more intelligent, anticipatory, and real-time conversational AI.
Read the full abstract ▾
All authors Ante Wang, Jiaqi Fu, Xuanyi Chen, Ruotian Ma, Zhaopeng Tu, Weizhi Ma, Yang Liu
Computation and Language · Cross-listed from cs.AI
Silicon Sampling via Cross-Survey Transfer
Chan-Tung Ku, Chan Hsu, Pei-Cing Huang et al. (+3 more)
Silicon sampling-using large
language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, most evaluations rely on distributional comparisons rather than individual-level prediction, which risks conflating pattern matching with coherent respondent-level prediction. We propose cross-survey transfer, a more rigorous evaluation framework in which an LLM is given a respondent's answers to one set of questions and must predict their answers to entirely different questions from the same survey. Using data from the Taiwan Election and Democratization Study (TEDS) 2024, three open-weight LLMs (27B-120B parameters), and supervised machine learning baselines, we find that: (1) zero-shot LLMs achieve 52% accuracy on genuinely unseen items, closing to within 6 percentage points (pp) of a supervised random forest trained on same-population data; (2) a stable construct predictability hierarchy emerges, from 67% for partisan attitudes to 23% for sovereignty; and (3) variance collapse and safety
alignment effects-two commonly cited LLM limitations-turn out to be more nuanced than previously reported, with variance collapse affecting supervised models as well and
alignment effects varying dramatically across model families. These findings clarify both the promise and boundaries of silicon sampling.
Read the full abstract ▾
All authors Chan-Tung Ku, Chan Hsu, Pei-Cing Huang, Frank Cheng-shan Liu, I-Ling Cheng, Yihuang Kang
Computation and Language
Alignment-Guided Largest Table Overlap Size Estimation
Ge Lee, Shixun Huang, Zhifeng Bao et al. (+2 more)
Fast estimation of the size of the largest overlap between tables enables blocking and query-by-table
retrieval in large table repositories. The first and the state-of-the-art
estimator Armadillo improves efficiency by
embedding each table independently and approximating overlap ratio via
embedding similarity. However, accurate estimation in heterogeneous repositories remains limited by three challenges: (C1) overlap depends on row-column structure, i.e., each matched
cell must preserve both its row and column membership under a joint
alignment of the two tables, but existing encodings leave this structure to be inferred indirectly; (C2) independent encoding provides no explicit channel for inter-table
alignment signals, biasing prediction toward global similarity; (C3) naive value encodings overfit to corpus-specific distributions, causing cross-domain degradation. Hence, we propose ALORE, a scalable and domain-robust overlap ratio
estimator built on three principles: (P1) explicitly represent row-column structure; (P2) expose inter-table
alignment signals during training without expensive
alignment search; (P3) reduce sensitivity to corpus-specific value distributions. ALORE instantiates these principles with a Two-View Row-Column Hypergraph encoder,
alignment-guided objectives with inexpensive interaction signals, and a domain-robust value mapping. Experiments on multiple
datasets spanning diverse domains and scales, including a large real-world corpus beyond prior
benchmarks, show that ALORE outperforms the state of the art. ALORE reduces MAE by up to 55% overall and 69% in zero-shot transfer, while achieving up to 89x speedup. We further validate its effectiveness for query-by-table
retrieval.
Read the full abstract ▾
All authors Ge Lee, Shixun Huang, Zhifeng Bao, Shazia Sadiq, Yanchang Zhao
Computation and Language · Cross-listed from cs.LG
Can Model Merging Improve Aggregation in DiLoCo?
Stefan Horoi, Benjamin Thérien, Guy Wolf et al. (+1 more)
Model merging techniques, which aggregate independently finetuned models into one to combine their capabilities, have become a topic of significant interest in recent years, with a broad array of methods having been proposed to tackle this problem. Simultaneously, an emerging trend in distributed learning has been the use of methods such as local SGD and DiLoCo, which greatly reduce communication costs by periodically aggregating the independently trained local models. However, these communication-efficient methods have been shown to degrade in performance relative to the FLOP-matched data-parallel gold standard as the number of independent local models grows and as the number of local training steps before global communication is increased. In this work, we draw an explicit analogy between the pseudo-gradient aggregation step in local SGD/DiLoCo and task arithmetic-based model merging, establishing a straightforward way to utilize merging methods in the context of distributed optimization. We then evaluate multiple state-of-the-art model merging methods in this setting and identify one method in particular, Iso-C, as a promising approach for improving DiLoCo. We find that DiLoCo SGD with Iso-C aggregation outperforms not only simple pseudo-gradient averaging but even the momentum-based DiLoCo, despite lacking a momentum mechanism itself. Building on this finding, we propose IsoLoCo, which adapts Iso-C for distributed training by equipping it with Nesterov momentum. Our empirical evaluations on
language model pre-training across varying numbers of local workers show that IsoLoCo significantly outperforms DiLoCo, with the gap between them widening as the number of workers increases. This advantage remains present across model sizes and inner step counts, confirming that merging-inspired aggregation is an effective strategy for low-communication distributed training.
Read the full abstract ▾
All authors Stefan Horoi, Benjamin Thérien, Guy Wolf, Eugene Belilovsky
Computation and Language
psytechlab at CLPsych 2026: Utilising Natural Language Processing methods and Large Language Models for Social Media Text Analysis
Igor Buyanov, Nafisa Valieva and Ekaterina Mazurina
Social media posts are a rich and valuable source of data for analyzing mental health states and users' well-being using automated analysis tools. In this work, we demonstrate how we used a range of Natural
Language Processing (NLP) methods, including Long Short-Term
Memory (LSTM), BERT-based models, and Large
Language Models (LLMs), for self-state and well-being analysis and summarization during the CLPsych Shared Task 2026. Our approach achieved one of the top Consistency and Contradiction scores for the summarization task and also middle-level results for the other tasks. By testing and developing such mental health-state estimation systems, we contributed to improving mental health support systems. We make our code available https://github.com/psytechlab/CLPsych2026/.
Read the full abstract ▾
Computation and Language
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Xiang Hu, Xinyu Wei, Hao Gu et al. (+10 more)
Scaling modern large
language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense
attention. Chunk-wise sparse
attention offers a promising alternative, but all existing methods fall short of full
attention because of their inaccurate chunk selection. We propose Hierarchical Landmark Sparse (HiLS)
Attention, a chunk-wise sparse
attention mechanism that learns chunk selection end-to-end under the
language-modeling (LM) loss. HiLS factorizes
attention hierarchically: each query performs
attention independently with each retrieved chunk to extract chunk-specific information, and the resulting outputs are fused according to chunk
retrieval scores. By incorporating
retrieval scores into the forward
attention computation, HiLS optimizes them directly with the LM loss, enabling end-to-end
retrieval learning and native sparse training. Experimental results show that HiLS-
Attention achieves performance comparable to, and in some cases better than, full
attention at in-domain context lengths. Meanwhile, HiLS-
Attention extrapolates more than $64\times$ the training context length with 90%
retrieval accuracy, far beyond full
attention. Moreover, existing full-
attention models can be converted to HiLS-
Attention with lightweight continued pretraining, preserving in-domain performance while acquiring ultra-long-context extrapolation. Together with its sparse KV access and computation, HiLS-
Attention breaks the usual efficiency-performance trade-off, enabling long-context LLMs that are both more efficient and more effective on general long-context tasks than their full-
attention counterparts.
Read the full abstract ▾
All authors Xiang Hu, Xinyu Wei, Hao Gu, Minshen Zhang, Tian Liang, Huayang Li, Lei Zhu, Yan Wang, Sirui Han, Yushi Bai, Kewei Tu, Haitao Mi, Leo Liang
Computation and Language · Cross-listed from cs.AI
Where Knowledge and Authority Sit Changes What an Agent Benchmark Can Resolve
Dan C. Hsu and Luke Lu
Most
agent benchmarks put facts, tools and permissions behind one interface. Real organizations spread them across people. Incognita asks what happens when the task and success criterion stay fixed but access does not. We transform eighteen customer-service tasks into three settings: direct access, one known intermediary, and six role-isolated participants whose capabilities must be discovered. Across 864 trials with four models, social access reduced success for every model; the pre-specified intervals excluded zero for two. The latest tested model, gpt-5.6-sol, achieved the highest social-access success at 0.65, a 0.11 decrease from centralized indirect access with an interval that included zero. Exploratory comparisons separated five of six model pairs under social access, while neither centralized setting separated any at this sample size. In post-hoc task-blocked tests, three pairwise interaction $p$-values remained significant after multiplicity adjustment. A reference-relative reader associates the wider gaps with failures to obtain needed information. Because the data cannot distinguish ineffective requests by the evaluated
agent from inaccurate replies by simulated participants, the reader's labels describe where trajectories stopped, not why models differed.
Read the full abstract ▾
Computation and Language
Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG
Haotian Zhou, Weiran Huang, Siqi Liu et al. (+3 more)
Cross-lingual
retrieval-augmented generation (RAG) is often deployed in an English-evidence regime, where users query in diverse
languages but retrieved passages remain English. In this setting, generation can fail despite strong base models: English evidence induces
language drift (English or code-switching outputs) and models use evidence unreliably when producing non-English answers. We attribute these failures to two post-training challenges: (i) errors are prefix-dependent, so fixed-trajectory supervision suffers from prefix mismatch; and (ii) sequence-level (partly discrete / judge-based) rewards yield noisy credit assignment and high-variance updates. We propose TR-RAG, a teacher-regularized RL recipe that couples reward optimization with on-policy
distillation on student-visited prefixes. A compact student samples on-policy answers, while a stronger frozen teacher is queried only on those prefixes and provides a prefix-wise student-to-teacher reverse-KL anchor. We further introduce a reward decomposition for English-evidence
multilingual generation, combining
language consistency, character 3-gram recall, and an LLM-judge score for evidence-grounded correctness. Across three
benchmarks (BioASQ-ENKB5, Hotpot-ENKB5, and naturally
multilingual MKQA) and two backbones, TR-RAG improves the composite of
language adherence and evidence-grounded correctness over strong baselines. Crucially, the teacher anchor acts as a safety net: on in-domain
languages it prevents the large
language-consistency collapses (up to ~27 percentage points) that reward-only RL can suffer by drifting below even the base model, while on distant out-of-distribution
languages, where reward-only RL stalls at the base model's ceiling, it still improves evidence grounding; and on character 3-gram recall the compact student sometimes surpasses its 70B teacher.
Read the full abstract ▾
All authors Haotian Zhou, Weiran Huang, Siqi Liu, Xiting Wang, Xin Zhang, Zhihao Wen
Computation and Language · Cross-listed from cs.LG
Individual Parameters in Weight-Sparse Transformers Appear Interpretable
Arnau Marin-Llobet and Stefan Heimersheim
A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does. Dominant
circuit-finding approaches focus on a specific behavior and reverse-engineer the role of components on the associated sub-distribution. However, past work has shown that components can have different functions that are active on different subsets of the input distribution. In this work we ask whether a single weight can be understood globally across the full training distribution by characterizing when it matters (the inputs on which ablating it changes the model's predictions). We introduce an automated LLM pipeline that writes a short, human-readable description of when a weight matters and verifies it on held-out text, crediting a weight only if its description generalizes. Across two sparse and two dense
transformers, the fraction of weights that are interpretable (in this sense) is higher in sparse
transformers than in dense ones, a gap that widens once unreliable descriptions are discarded. Our results show that a meaningful fraction of a sparse
transformer model's weights can be interpreted: 12 to 31% of weights have a single short description that identifies what the weight is used for.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
Long Xu, Binghong Wu, Tinghao Yu et al. (+6 more)
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing
benchmarks predominantly focus on high-resource
languages like English and Chinese, creating an evaluation blind spot concerning model performance on other
languages. While recent
Vision-
Language Models (VLMs) claim support for hundreds of
languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introduce MORE, a large-scale
benchmark designed for
multilingual document parsing evaluation. MORE distinguishes itself through three key dimensions: (1) Unprecedented Scale: It covers 149
languages, making it the most linguistically diverse
benchmark to date; (2) Structural Complexity: Unlike previous works, it extends evaluation beyond plain text to include structural elements such as code blocks, tables, and catalogs; and (3) Data Authenticity: All samples are curated from real-world documents via a model-assisted, human-refined annotation pipeline. We evaluate state-of-the-art models using MORE, establishing new performance baselines for long-tail
languages and validating the
benchmark's effectiveness in diagnosing model capabilities in realistic, diverse scenarios. The MORE
dataset will be available at https://github.com/zimoqingfeng/MORE.
Read the full abstract ▾
All authors Long Xu, Binghong Wu, Tinghao Yu, Hao Feng, Zhenyu Huang, Haoqing Jiang, Yunhao Wang, Shuo Huang, Feng Zhang
Computation and Language · Cross-listed from econ.GN
FOI-O: A global ontology and verification framework for Freedom of Information process modelling
Dylan A Mordaunt
Public official-information request records contain process signals. They can support research, workflow review, and analyst-led assessment. Yet they also mix observed correspondence, platform states, inferred events, and legal outcomes. FOI-O is a reusable process-modelling method and verification infrastructure for Freedom of Information administration. It is a global model that began with the New Zealand Official Information Act and has since iterated through the Australian Commonwealth and New South Wales settings. The NZ package remains the mature reference implementation; the Australian work remains provisional pending empirical evaluation and jurisdiction-specific legal validation. FOI-O models request records, observed correspondence, controlled vocabularies, provenance, review queues, release metadata, and bounded analysis rules. Legally meaningful outcomes require certification by an authorised decision-maker. Its typed operational and semantic contracts are supported by deterministic examples, process models, fixture-only process-mining exports, quality gates, and tests. This article describes the motivation, architecture, ontology-development method, its versioned extraction and review protocol, how related repositories share data and evidence, and how the method may be adapted for Australia, validation evidence, and implementation boundaries. The project is not legal advice, is not an official government publication, and does not certify release, refusal, redaction, charging, extension, transfer, complaint, or publication outcomes.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space
Peiming Li, Yifan Wang, Xiaotian Zhang et al. (+4 more)
Multimodal Large
Language Models (MLLMs) have achieved remarkable progress but still struggle with complex visual
reasoning tasks requiring multi-step perception and logical deduction. While explicit visual generation incurs prohibitive computational costs, existing latent approaches often rely on external experts or lack rigorous cognitive logic. In this paper, we introduce ProLaViT (Progressive Latent Visual Thought), a framework empowering MLLMs to perform structured visual derivation in the continuous latent space. Unlike works dependent on heterogeneous external models, ProLaViT leverages an endogenous self-
distillation mechanism, utilizing the model's own visual encoder to supervise latent thoughts. To facilitate this, we construct a scalable programmatic synthesis pipeline enabling the model to internalize algorithmic precision without inference time tools. We design two
reasoning paradigms: (1) Coarse-to-Fine Causal Chain for spatial tasks, guiding
attention from global context to local targets. (2) Dialectical
Reasoning Chain for logical tasks, incorporating counter-factual thinking for verification. Furthermore, we propose a Distance-Weighted Diversity Loss to impose
topology-aware constraints, preventing feature degeneration by enforcing semantic distinctiveness. Extensive experiments demonstrate that ProLaViT outperforms baselines on
vision-centric
benchmarks, achieving superior accuracy and interpretability with high efficiency.
Read the full abstract ▾
All authors Peiming Li, Yifan Wang, Xiaotian Zhang, Zhiyuan Hu, Shiyu Li, Zheng Wei, Yang Tang
Computation and Language · Cross-listed from cs.SI
Angry but Accurate: Detecting and Profiling the Counter-Misinformation Ecosystem on Twitter
Eun Cheol Choi and Emilio Ferrara
On social media, many users actively push back against false claims. Understanding who pushes back and how they do so matters, as this corrective activity is central to how misinformation is contested. We study this counter-misinformation ecosystem at scale: applying a domain-specific NLI model from our prior work to a large corpus of COVID-19 tweets, we classify 264,737 posts as supporting or opposing false claims and compare 23 user- and text-level features across the two groups. Contrary to the dominant assumption that negative
emotion is a signature of falsehood, we find that misinformation-opposing posts are more emotionally negative than misinformation-supporting posts, with higher levels of anger, disgust, and sadness. These differences are modest in magnitude but consistent in direction across the negative
emotions. We also find that posts opposing misinformation tend to come from more established users, i.e., older accounts, more followers, and higher listed counts.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models
Hamish Ogilvy
Low-bit quantization shrinks
language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width. We introduce Variable Bit-width Quantization (VBQ), a training-time method in which each contiguous group of 64 weights learns its own resolution from {1,2,4,8} bits via a Gumbel-Softmax relaxation, trained jointly by an alternating optimization that gives the precision logits a clean, task-aligned signal. VBQ discovers a consistent, strongly heterogeneous allocation within individual projection types, not merely across layers, impossible to express with per-layer methods: 69% of groups collapse to 1 bit, the LM head averages 1.09 bits, while the first MLP block keeps ~2.5 bits. This pattern is stable enough to freeze into a fixed recipe and reuse without further search. The recipe yields a "bigger-but-smaller" regime: a 131M model at 1.82 mean bits reaches perplexity 4.2 on TinyStories, beating a 55M FP16 model (PPL 4.4) at 3.8x less storage, and lets a 1.46B model on FineWeb-Edu match a 593M FP16 control at ~3.7x less storage with 2.5x more parameters. As quality-per-byte, VBQ is 3.9-8.4x more efficient than FP16. The recipe maps directly to packed low-bit storage, so it also accelerates inference: with custom fused dequantize-and-multiply kernels,
memory-bandwidth-bound autoregressive decode is faster at equal output, and the speedup grows with scale (parity at 131M, 1.9x at 1.0B, 4.7x at 9B on Apple silicon). A distributional analysis (KL divergence and argmax-flip rate) reveals a striking mechanism: deeper layers progressively self-heal the quantization error injected by early layers. The win is a from-scratch, train-time phenomenon; scaling the search economically beyond 1.5B parameters remains open. VBQ reframes precision as a learnable, non-uniform resource and shows that spending a fixed bit budget unevenly beats spending it uniformly.
Read the full abstract ▾
Computation and Language
Where do LLMs Fall Short in CBT-Guided Affective Reasoning?
Vaishnavi Sinha, Pooja Guttal, Pranay Deep Reddy Katike et al. (+5 more)
Cognitive Behavioral Therapy (CBT) provides a structured framework for understanding a user's mental state by examining the interaction between cognitive and behavioral factors. However, out-of-the-box LLMs respond fluently and empathetically, yet collapse into validation & reflection, regardless of what the user actually needs. They know theoretical CBT (scoring up to 96% accuracy on licensing exam questions) but fail to apply it effectively. We explore this gap with a knowledge-guided framework that treats CBT dialogue as controlled affective
reasoning: user narratives are decomposed into Beck's Cognitive Conceptualization structure, grounded in clinical SNOMED CT concepts validated via Natural
Language Inference, and a Multiple Chain-of-Thought (MCoT) strategy selection between Validation & Reflection, Socratic Questioning, or Alternative Perspectives. To measure whether such guidance actually changes behavior, we introduce the Protocol Leverage Force (F), a behavior-level metric that captures how far an intervention shifts a model away from its default response. Across three open-weight LLMs and 14 RealCBT-derived case studies, evaluated with human experts, valence-arousal trajectories, and linguistic entrainment, F shows that simply introducing protocol definitions via single chain-of-thought prompting fails to change LLM behavior, while MCoT on these definitions guides strategy selection better. Still, the effect stays within 1% (approx. 1.2-1.3%), and all models remain biased toward Validation & Reflection. These results show CBT knowledge alone does not ensure effective application, giving the affective-computing community instrumentation to measure where LLMs fall short.
Read the full abstract ▾
All authors Vaishnavi Sinha, Pooja Guttal, Pranay Deep Reddy Katike, Vishal Sinha, Gerald Ndawula, Lira Yoon, Andrea Kleinsmith, Manas Gaur
Computation and Language
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Zhuoqun Li, Boxi Cao, Jiawei Chen et al. (+11 more)
Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of large
language models (LLMs) offers a promising direction for sequential behavior prediction, yet LLMs struggle with latent behavioral pattern induction and model-intrinsic cognitive biases when tackling long-horizon behavior prediction. Prior
memory management methods follow a context-compression paradigm that attempts to address this task by alleviating the historical sequence burden, yet fail to resolve the core challenges. In this paper, we advocate a paradigm shift that reframes the lengthy historical sequence from a burden into a valuable resource to be exploited, and accordingly propose PraMem, which conducts beforehand practice over the lengthy historical sequence to build an experiential
memory, thereby serving as the assisted input for accurate long-horizon behavior prediction. Extensive experiments across diverse tasks demonstrate that PraMem achieves superior performance than prior methods, and more in-depth analyses provide valuable insights into the mechanism and
evolution of the experiential
memory. Code: https://github.com/icip-cas/PraMem.
Read the full abstract ▾
All authors Zhuoqun Li, Boxi Cao, Jiawei Chen, Hanshu Zhou, Ruoxi Xu, Guiping Jiang, Ruotong Pan, Tingting Gao, Han Li, Xiangyu Wu, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun
Computation and Language
Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion
Saurabh Kumar, Amartyaveer and Prasanta Kumar Ghosh
Automatic
Speech Recognition (ASR) and Dialect Identification (DID) are crucial for Indian
languages, many of which are low-resource and exhibit significant dialectal differences. Existing methods often optimize ASR or DID individually, resulting in performance trade-offs. In this work, we propose a
multimodal framework that jointly improves ASR and DID. Our method employs a Bottleneck Encoder to extract dialectal features from Conformer-based
speech representations and a RoBERTa encoder to process ASR-generated CTC
embeddings. A gating mechanism merges these features, followed by an
attention encoder to refine the representations. The learned
embeddings are concatenated with Conformer outputs to enhance ASR features. Evaluated on eight Indian
languages with thirty-three dialects, our method achieves an average DID accuracy of 81.63% and average CER and WER of 4.65% and 17.73%, respectively. These results highlight the effectiveness of our method for joint ASR-DID modeling.
Read the full abstract ▾