Computation and Language
PVminer: A Domain-Specific Tool to Detect the Patient Voice in Patient Generated Data
Samah Fodeh, Linhai Ma, Yan Wang et al. (+6 more)
Patient-generated text such as secure messages, surveys, and interviews contains rich expressions of the patient voice (PV), reflecting communicative behaviors and social determinants of health (SDoH). Traditional qualitative coding frameworks are labor intensive and do not scale to large volumes of patient-authored messages across health systems. Existing machine learning (ML) and natural
language processing (NLP) approaches provide partial solutions but often treat patient-centered communication (PCC) and SDoH as separate tasks or rely on models not well suited to patient-facing
language. We introduce PVminer, a domain-adapted NLP framework for structuring patient voice in secure patient-provider communication. PVminer formulates PV detection as a multi-label, multi-class prediction task integrating patient-specific BERT encoders (PV-BERT-base and PV-BERT-large), unsupervised topic modeling for thematic augmentation (PV-Topic-BERT), and fine-tuned classifiers for Code, Subcode, and Combo-level labels. Topic representations are incorporated during fine-tuning and inference to enrich semantic inputs. PVminer achieves strong performance across hierarchical tasks and outperforms biomedical and clinical pre-trained baselines, achieving F1 scores of 82.25% (Code), 80.14% (Subcode), and up to 77.87% (Combo). An ablation study further shows that author identity and topic-based augmentation each contribute meaningful gains. Pre-trained models, source code, and documentation will be publicly released, with annotated
datasets available upon request for research use.
Read the full abstract ▾
All authors Samah Fodeh, Linhai Ma, Yan Wang, Srivani Talakokkul, Ganesh Puthiaraju, Afshan Khan, Ashley Hagaman, Sarah Lowe, Aimee Roundtree
Computation and Language · Cross-listed from cs.LG
SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards
Dengjia Zhang, Xiaoou Liu, Lu Cheng et al. (+3 more)
Large
language models (LLMs) are increasingly deployed as multi-step decision-making
agents, where effective reward design is essential for guiding learning. Although recent work explores various forms of reward shaping and step-level credit assignment, a key signal remains largely overlooked: the intrinsic uncertainty of LLMs. Uncertainty reflects model confidence, reveals where exploration is needed, and offers valuable learning cues even in failed trajectories. We introduce SELAUR: Self Evolving LLM
Agent via Uncertainty-aware Rewards, a reinforcement learning framework that incorporates uncertainty directly into the reward design. SELAUR integrates
entropy-, least-confidence-, and margin-based metrics into a combined
token-level uncertainty estimate, providing dense confidence-aligned supervision, and employs a failure-aware reward reshaping mechanism that injects these uncertainty signals into step- and trajectory-level rewards to improve exploration efficiency and learning stability. Experiments on two
benchmarks, ALFWorld and WebShop, show that our method consistently improves success rates over strong baselines. Ablation studies further demonstrate how uncertainty signals enhance exploration and robustness.
Read the full abstract ▾
All authors Dengjia Zhang, Xiaoou Liu, Lu Cheng, Yaqing Wang, Kenton Murray, Hua Wei
Computation and Language · Cross-listed from cs.AI
A Benchmark for Deep Information Synthesis
Debjit Paul, Daniel Murphy, Milan Gritta et al. (+14 more)
Large
language model (LLM)-based
agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation
benchmarks do not adequately assess their ability to solve real-world tasks that require synthesizing information from multiple sources and inferring insights beyond simple fact
retrieval. To address this, we introduce DEEPSYNTH, a novel
benchmark designed to evaluate
agents on realistic, time-consuming problems that combine information gathering, synthesis, and structured
reasoning to produce insights. DEEPSYNTH contains 120 tasks collected across 7 domains and data sources covering 67 countries. DEEPSYNTH is constructed using a multi-stage data collection pipeline that requires annotators to collect official data sources, create hypotheses, perform manual analysis, and design tasks with verifiable answers. When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research
agents achieve a maximum F1 score of 8.97 and 17.5 on the LLM-judge metric, underscoring the difficulty of the
benchmark. Our analysis reveals that current
agents struggle with
hallucinations and
reasoning over large information spaces, highlighting DEEPSYNTH as a crucial
benchmark for guiding future research.
Read the full abstract ▾
All authors Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger, Aysim Toker, Roy Miles, Andreea-Maria Oncescu, Jasivan Alex Sivakumar, Philipp Borchert, Ismail Elezi, Meiru Zhang, Ka Yiu Lee, Guchun Zhang, Jun Wang, Gerasimos Lampouras
Computation and Language
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning
Sanket Badhe and Deep Shah
Advanced
reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternative, fine-tuning smaller models, often sacrifices interpretability while introducing significant resource and operational overhead. To address these limitations, we introduce
Prompt-Level
Distillation (PLD). We extract explicit
reasoning patterns from a Teacher model and organize them into a structured list of expressive instructions for the Student model's System
Prompt. Evaluated using Gemma-3 4B, PLD improved Macro F1 scores on StereoSet (57% to 90.0%) and Contract-NLI (67% to 83%), while increasing LogiQA accuracy to 70%. Similar results on Mistral Small 3.1 demonstrate cross-architecture generalizability, enabling these compact models to match frontier performance with negligible latency overhead. These expressive instructions render the decision-making process transparent, allowing for full human verification of logic, making this approach ideal for regulated industries such as law, finance, and content moderation, as well as high-volume use cases and edge devices.
Read the full abstract ▾
Computation and Language
Beyond the Star Rating: A Scalable Framework for Aspect-Based Sentiment Analysis Using LLMs and Text Classification
Vishal Patil, Shree Vaishnavi Bacha, Revanth Yamani et al. (+2 more)
Customer-provided reviews have become an important source of information for business owners and other customers alike. However, effectively analyzing millions of unstructured reviews remains challenging. While large
language models (LLMs) show promise for natural
language understanding, their application to large-scale review analysis has been limited by computational costs and scalability concerns. This study proposes a hybrid approach that uses LLMs for aspect identification while employing classic machine-learning methods for sentiment classification at scale. Using ChatGPT to analyze sampled restaurant reviews, we identified key aspects of dining experiences and developed sentiment classifiers using human-labeled reviews, which we subsequently applied to 4.7 million reviews collected over 17 years from a major online platform. Regression analysis reveals that our machine-labeled aspects significantly explain variance in overall restaurant ratings across different aspects of dining experiences, cuisines, and geographical regions. Our findings demonstrate that combining LLMs with traditional machine learning approaches can effectively automate aspect-based sentiment analysis of large-scale customer feedback, suggesting a practical framework for both researchers and practitioners in the hospitality industry and potentially, other service sectors.
Read the full abstract ▾
All authors Vishal Patil, Shree Vaishnavi Bacha, Revanth Yamani, Yidan Sun, Mayank Kejriwal
Computation and Language · Cross-listed from cs.HC
An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems
Anna Martin-Boyle, William Humphreys, Martha Brown et al. (+2 more)
Large
Language Models (LLMs) are transforming scholarly tasks like search and summarization, but their reliability remains uncertain. Current evaluation metrics for testing LLM reliability are primarily automated approaches that prioritize efficiency and scalability, but lack contextual nuance and fail to reflect how scientific domain experts assess LLM outputs in practice. We developed and validated a schema for evaluating LLM errors in scholarly question-answering systems that reflects the assessment strategies of practicing scientists. In collaboration with domain experts, we identified 20 error patterns across seven categories through thematic analysis of 68 question-answer pairs. We validated this schema through contextual inquiries with 10 additional scientists, which showed not only which errors experts naturally identify but also how structured evaluation schemas can help them detect previously overlooked issues. Domain experts use systematic assessment strategies, including technical precision testing, value-based evaluation, and meta-evaluation of their own practices. We discuss implications for supporting expert evaluation of LLM outputs, including opportunities for personalized, schema-driven tools that adapt to individual evaluation patterns and expertise levels.
Read the full abstract ▾
All authors Anna Martin-Boyle, William Humphreys, Martha Brown, Cara Leckey, Harmanpreet Kaur
Computation and Language · Cross-listed from cs.CV
VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
Seongheon Park, Changdae Oh, Hyeong Kyu Choi et al. (+2 more)
Large
Vision-
Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can improve deployment reliability; however, they depend heavily on
language priors and are therefore ill-suited for evaluating
vision-conditioned predictions. We propose VAUQ, a
vision-aware uncertainty quantification framework for LVLM self-evaluation that explicitly measures how strongly a model's output depends on visual evidence. VAUQ introduces the Image-Information Score (IS), which captures the reduction in predictive uncertainty attributable to visual input, and an unsupervised core-region masking strategy that amplifies the influence of salient regions. Combining predictive
entropy with this core-masked IS yields a training-free scoring function that reliably reflects answer correctness. Comprehensive experiments show that VAUQ consistently outperforms existing self-evaluation methods across multiple
datasets.
Read the full abstract ▾
All authors Seongheon Park, Changdae Oh, Hyeong Kyu Choi, Sean Du, Sharon Li
Computation and Language · Cross-listed from cs.HC
PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A
Anna Martin-Boyle, Cara A.C. Leckey, Martha C. Brown et al. (+1 more)
Large
language models (LLMs) are increasingly used in scholarly question-answering (QA) systems to help researchers synthesize vast amounts of literature. However, these systems often produce subtle errors (e.g., unsupported claims, errors of omission), and current provenance mechanisms like source citations are not granular enough for the rigorous verification that scholarly domain requires. To address this, we introduce PaperTrail, a novel interface that decomposes both LLM answers and source documents into discrete claims and evidence, mapping them to reveal supported assertions, unsupported claims, and information omitted from the source texts. We evaluated PaperTrail in a within-subjects study with 26 researchers who performed two scholarly editing tasks using PaperTrail and a baseline interface. Our results show that PaperTrail significantly lowered participants' trust compared to the baseline. However, this increased caution did not translate to behavioral changes, as people continued to rely on LLM-generated scholarly edits to avoid a cognitively burdensome task. We discuss the value of claim-evidence matching for understanding LLM trustworthiness in scholarly settings, and present design implications for cognition-friendly communication of provenance information.
Read the full abstract ▾
All authors Anna Martin-Boyle, Cara A.C. Leckey, Martha C. Brown, Harmanpreet Kaur
Computation and Language · Cross-listed from cs.IR
HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
Kun Yuan, Junyu Bi, Daixuan Cheng et al. (+5 more)
Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and
memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-
agents as fine-grained preference centers. Guided by these
agents, Soft-Routing
Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift – demonstrating its scalability and real-world effectiveness.
Read the full abstract ▾
All authors Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao, Binbin Cao, Jian Wu, Yuning Jiang
Computation and Language · Cross-listed from cs.IR
Generative Pseudo-Labeling for Pre-Ranking with LLMs
Junyu Bi, Xinting Niu, Daixuan Cheng et al. (+4 more)
Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only on exposed interactions, yet must score all recalled candidates – including unexposed items – during online serving. This mismatch not only induces severe sample selection bias but also degrades generalization, especially for long-tail content. Existing debiasing approaches typically rely on heuristics (e.g., negative sampling) or
distillation from biased rankers, which either mislabel plausible unexposed items as negatives or propagate exposure bias into pseudo-labels. In this work, we propose Generative Pseudo-Labeling (GPL), a framework that leverages large
language models (LLMs) to generate unbiased, content-aware pseudo-labels for unexposed items, explicitly aligning the training distribution with the online serving space. By offline generating user-specific interest anchors and matching them with candidates in a frozen semantic space, GPL provides high-quality supervision without adding online latency. Deployed in a large-scale production system, GPL improves click-through rate by 3.07%, while significantly enhancing recommendation diversity and long-tail item discovery.
Read the full abstract ▾
All authors Junyu Bi, Xinting Niu, Daixuan Cheng, Kun Yuan, Tao Wang, Binbin Cao, Jian Wu
Computation and Language · Cross-listed from eess.IV
Multimodal MRI Report Findings Supervised Brain Lesion Segmentation with Substructures
Yubin Ge, Yongsong Huang and Xiaofeng Liu
Report-supervised (RSuper) learning seeks to alleviate the need for dense tumor voxel labels with constraints derived from radiology reports (e.g., volumes, counts, sizes, locations). In MRI studies of
brain tumors, however, we often involve multi-parametric scans and substructures. Here, fine-grained modality/parameter-wise reports are usually provided along with global findings and are correlated with different substructures. Moreover, the reports often describe only the largest lesion and provide qualitative or uncertain cues (“mild,” “possible”). Classical RSuper losses (e.g., sum volume consistency) can over-constrain or hallucinate unreported findings under such incompleteness, and are unable to utilize these hierarchical findings or exploit the priors of varied lesion types in a merged
dataset. We explicitly parse the global quantitative and modality-wise qualitative findings and introduce a unified, one-sided, uncertainty-aware formulation (MS-RSuper) that: (i) aligns modality-specific qualitative cues (e.g., T1c enhancement, FLAIR edema) with their corresponding substructures using existence and absence losses; (ii) enforces one-sided lower-bounds for partial quantitative cues (e.g., largest lesion size, minimal multiplicity); and (iii) adds extra- vs. intra-axial anatomical priors to respect cohort differences. Certainty
tokens scale penalties; missing cues are down-weighted. On 1238 report-labeled BraTS-MET/MEN scans, our MS-RSuper largely outperforms both a sparsely-supervised baseline and a naive RSuper method.
Read the full abstract ▾
Computation and Language
Evaluating Proactive Risk Awareness of Large Language Models
Xuan Luo, Yubin Chen, Zhiyu Hou et al. (+4 more)
As large
language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward anticipating unintended but consequential risks. In this work, we introduce a proactive risk awareness evaluation framework that measures whether LLMs can anticipate potential harms and provide warnings before damage occurs. We construct the Butterfly
dataset to instantiate this framework in the environmental and ecological domain. It contains 1,094 queries that simulate ordinary solution-seeking activities whose responses may induce latent ecological impact. Through experiments across five widely used LLMs, we analyze the effects of response length,
languages, and modality. Experimental results reveal consistent, significant declines in proactive awareness under length-restricted responses, cross-lingual similarities, and persistent blind spots in (
multimodal) species protection. These findings highlight a critical gap between current safety
alignment and the requirements of real-world ecological responsibility, underscoring the need for proactive safeguards in LLM deployment.
Read the full abstract ▾
All authors Xuan Luo, Yubin Chen, Zhiyu Hou, Linpu Yu, Geng Tu, Jing Li, Ruifeng Xu
Computation and Language
Linear Reasoning vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving
Yuliang Ji, Fuchen Shen, Jian Wu et al. (+2 more)
To comprehensively evaluate the mathematical
reasoning capabilities of Large
Language Models (LLMs), researchers have introduced abundant mathematical
reasoning datasets. However, most existing
datasets primarily focus on linear
reasoning, neglecting other parts such as proof by contradiction and proof by cases, which are crucial for investigating LLMs'
reasoning abilities. To address this limitation, we first introduce a novel first-order logic (FOL)
dataset named PC-FOL, annotated by professional mathematicians, focusing on case-based
reasoning problems. All instances in this
dataset are equipped with a manually written natural
language proof, clearly distinguishing it from conventional linear
reasoning datasets. Our experimental results over leading LLMs demonstrate a substantial performance gap between linear
reasoning and case-based
reasoning problems. To further investigate this phenomenon, we provide a theoretical analysis grounded in graphical model, which provides an explanation for the observed disparity between the two types of
reasoning problems. We hope this work can reveal the core challenges in the field of automated natural
language mathematical proof generation, paving the way for future research.
Read the full abstract ▾
All authors Yuliang Ji, Fuchen Shen, Jian Wu, Qiujie Xie, Yue Zhang
Computation and Language
Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Models
Paola Merlo, Chunyang Jiang, Giuseppe Samo et al. (+1 more)
This article describes a novel
language task, the Blackbird
Language Matrices (BLM) task, inspired by intelligence tests, and illustrates the BLM
datasets, their construction and benchmarking, and targeted experiments on chunking and systematicity. BLMs are multiple-choice problems, structured at multiple levels: within each sentence, across the input sequence, within each candidate answer. Because of their rich structure, these curated, but naturalistic
datasets are key to answer some core questions about current large
language models abilities: do LLMs detect linguistic objects and their properties? Do they detect and use systematic patterns across sentences? Are they more prone to linguistic or
reasoning errors, and how do these interact? We show that BLMs, while challenging, can be solved at good levels of performance, in more than one
language, with simple baseline models or, at better performance levels, with more tailored models. We show that their representations contain the grammatical objects and attributes relevant to solve a linguistic task. We also show that these solutions are reached by detecting systematic patterns across sentences. The paper supports the point of view that curated, structured
datasets support multi-faceted investigations of properties of
language and large
language models. Because they present a curated, articulated structure, because they comprise both learning contexts and expected answers, and because they are partly built by hand, BLMs fall in the category of
datasets that can support explainability investigations, and be useful to ask why large
language models behave the way they do.
Read the full abstract ▾
All authors Paola Merlo, Chunyang Jiang, Giuseppe Samo, Vivi Nastase
Computation and Language
The Art of Efficient Reasoning: Data, Reward, and Optimization
Taiqiang Wu, Zenan Xu, Bo Zhou et al. (+1 more)
Large
Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT)
reasoning, but also suffer from heavy computational overhead. To address this issue, efficient
reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL). In this paper, we systematically investigate the mechanics of efficient
reasoning for LLMs. For comprehensive evaluation, we advocate for more fine-grained metrics, including length distribution conditioned on correctness and performance across a wide spectrum of
token budgets ranging from 2k to 32k. First, we reveal that the training process follows a two-stage paradigm: length adaptation and
reasoning refinement. Through extensive experiments (about 0.2 million GPU hours) in a unified protocol, we deconstruct training
prompts and rollouts, reward shaping, and optimization strategies. A central finding is to maintain a sufficient density of positive reward signals and avoid the short-is-correct trap. Moreover, the learned length bias generalizes across domains and difficulty levels. We distill these findings into valuable insights and practical guidelines, and validate them across the Qwen3 models ranging from 0.6B to 30B, demonstrating the robustness and generalization. Weights are available at https://wutaiqiang.github.io/project/Art
Read the full abstract ▾
All authors Taiqiang Wu, Zenan Xu, Bo Zhou, Ngai Wong
Computation and Language · Cross-listed from cs.AI
Predicting Sentence Acceptability Judgments in Multimodal Contexts
Hyewon Jang, Nikolai Ilinykh, Sharid Loáiciga et al. (+2 more)
Previous work has examined the capacity of deep neural networks (DNNs), particularly
transformers, to predict human sentence acceptability judgments, both independently of context, and in document contexts. We consider the effect of prior exposure to visual images (i.e., visual context) on these judgments for humans and large
language models (LLMs). Our results suggest that, in contrast to textual context, visual images appear to have little if any impact on human acceptability ratings. However, LLMs display the compression effect seen in previous work on human judgments in document contexts. Different sorts of LLMs are able to predict human acceptability judgments to a high degree of accuracy, but in general, their performance is slightly better when visual contexts are removed. Moreover, the distribution of LLM judgments varies among models, with Qwen resembling human patterns, and others diverging from them. LLM-generated predictions on sentence acceptability are highly correlated with their normalised log probabilities in general. However, the correlations decrease when visual contexts are present, suggesting that a higher gap exists between the internal representations of LLMs and their generated predictions in the presence of visual contexts. Our experimental work suggests interesting points of similarity and of difference between human and LLM processing of sentences in
multimodal contexts.
Read the full abstract ▾
All authors Hyewon Jang, Nikolai Ilinykh, Sharid Loáiciga, Jey Han Lau, Shalom Lappin
Computation and Language
Exa-PSD: a new Persian sentiment analysis dataset on Twitter
Seyed Himan Ghaderi, Saeed Sarbazi Azad, Mohammad Mehdi Jaziriyan et al. (+1 more)
Today, Social networks such as Twitter are the most widely used platforms for communication of people. Analyzing this data has useful information to recognize the opinion of people in tweets. Sentiment analysis plays a vital role in NLP, which identifies the opinion of the individuals about a specific topic. Natural
language processing in Persian has many challenges despite the adventure of strong
language models. The
datasets available in Persian are generally in special topics such as products, foods, hotels, etc while users may use ironies, colloquial phrases in social media To overcome these challenges, there is a necessity for having a
dataset of Persian sentiment analysis on Twitter. In this paper, we introduce the Exa sentiment analysis Persian
dataset, which is collected from Persian tweets. This
dataset contains 12,000 tweets, annotated by 5 native Persian taggers. The aforementioned data is labeled in 3 classes: positive, neutral and negative. We present the characteristics and statistics of this
dataset and use the pre-trained Pars Bert and Roberta as the base model to evaluate this
dataset. Our evaluation reached a 79.87 Macro F-score, which shows the model and data can be adequately valuable for a sentiment analysis system.
Read the full abstract ▾
All authors Seyed Himan Ghaderi, Saeed Sarbazi Azad, Mohammad Mehdi Jaziriyan, Ahmad Akbari
Computation and Language
FinAnchor: Aligned Multi-Model Representations for Financial Prediction
Zirui He, Huopu Zhang, Yanguang Liu et al. (+2 more)
Financial prediction from long documents involves significant challenges, as actionable signals are often sparse and obscured by noise, and the optimal LLM for generating
embeddings varies across tasks and time periods. In this paper, we propose FinAnchor(Financial Anchored Representations), a lightweight framework that integrates
embeddings from multiple LLMs without fine-tuning the underlying models. FinAnchor addresses the incompatibility of feature spaces by selecting an anchor
embedding space and learning linear mappings to align representations from other models into this anchor. These aligned features are then aggregated to form a unified representation for downstream prediction. Across multiple financial NLP tasks, FinAnchor consistently outperforms strong single-model baselines and standard ensemble methods, demonstrating the effectiveness of anchoring heterogeneous representations for robust financial prediction.
Read the full abstract ▾
All authors Zirui He, Huopu Zhang, Yanguang Liu, Sirui Wu, Mengnan Du
Computation and Language
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
Sayantan Dasgupta, Trevor Cohn and Timothy Baldwin
The core learning signal used in
language model
distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distributions. Traditional KL divergence tends to be dominated by the next
tokens with the highest probabilities, i.e., the teacher's modes, thereby diminishing the influence of less probable yet potentially informative components of the output distribution. We propose a new tail-aware divergence that decouples the contribution of the teacher model's top-K predicted probabilities from that of lower-probability predictions, while maintaining the same computational profile as the KL Divergence. Our decoupled approach reduces the impact of the teacher modes and, consequently, increases the contribution of the tail of the distribution. Experimental results demonstrate that our modified
distillation method yields competitive performance in both pre-training and supervised
distillation of decoder models across various
datasets. Furthermore, the
distillation process is efficient and can be performed with a modest academic budget for large
datasets, eliminating the need for industry-scale computing.
Read the full abstract ▾
Computation and Language
Overton Pluralistic Reinforcement Learning for Large Language Models
Yu Fu, Seongho Son and Ilija Bogunovic
Existing
alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism (OP) addresses this gap by generating responses with diverse perspectives from a single query. This paper introduces OP-GRPO (Overton Pluralistic Group Relative Policy Optimization), a reinforcement learning framework for implicit Overton Pluralism that enables a single LLM to produce pluralistic responses without explicit prompting or modular orchestration. Our workflow consists of two main steps: 1) Similarity
estimator training, which fine-tunes a Sentence
Transformer for OP tasks to provide a more accurate coverage evaluation of the given responses; and 2) OP-GRPO training, which incorporates this similarity
estimator into a carefully designed dual-reward system to ensure both broad coverage of genuine human perspectives and the uniqueness of each perspective, thereby promoting diversity. Empirical results demonstrate that OP-GRPO achieves a "Small models, Big perspective coverage" effect: our trained Qwen2.5-3B-Instruct surpasses the GPT-OSS (20B) baseline with a 37.4% relative accuracy gain on the Natural
Language Inference (NLI)
benchmark. It also outperforms a modular-architecture baseline with a 19.1% relative improvement. Evaluations with GPT-5.4 as the LLM judge and OP-
Benchmark further confirm the robustness of our approach.
Read the full abstract ▾
Computation and Language
SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing
Yifei Xu, Guilherme Potje, Shivam Shandilya et al. (+9 more)
Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training. Rubrics provide structured, interpretable supervision, but scaling rubric construction is difficult: expert rubrics are costly, prompted rubrics are often superficial or inconsistent, and fixed-pool discriminative rubrics can saturate and drift, enabling reward hacking. We present SibylSense, an inference-time learning approach that adapts a frozen rubric generator through a tunable
memory bank of validated rubric items.
Memory is updated via verifier-based item rewards measured by reference-candidate answer discriminative gaps from a handful of examples. SibylSense alternates
memory tuning with a rubric-
adversarial policy update that produces rubric-satisfying candidate answers, shrinking discriminative gaps and driving the rubric generator to capture new quality dimensions. Experiments on two open-ended tasks show that SibylSense yields more discriminative rubrics and improves downstream RL performance over static and non-adaptive baselines.
Read the full abstract ▾
All authors Yifei Xu, Guilherme Potje, Shivam Shandilya, Tiancheng Yuan, Leonardo de Oliveira Nunes, Rakshanda Agarwal, Saeid Asgari, Adam Atkinson, Emre K{\i}c{\i}man, Songwu Lu, Ranveer Chandra, Tusher Chakraborty
Computation and Language
Explicit Grammar Semantic Feature Fusion for Robust Text Classification
Azrin Sultana and Firoz Ahmed
Natural
Language Processing enables computers to understand human
language by analysing and classifying text efficiently with deep-level grammatical and semantic features. Existing models capture features by learning from large corpora with
transformer models, which are computationally intensive and unsuitable for resource-constrained environments. Therefore, our proposed study incorporates comprehensive grammatical rules alongside semantic information to build a robust, lightweight classification model without resorting to full parameterised
transformer models or heavy deep learning architectures. The novelty of our approach lies in its explicit encoding of sentence-level grammatical structure, including syntactic composition, phrase patterns, and complexity indicators, into a compact grammar vector, which is then fused with frozen contextual
embeddings. These heterogeneous elements unified a single representation that captures both the structural and semantic characteristics of the text. Deep learning models such as Deep Belief Networks (DBNs), Long Short-Term
Memory (LSTMs), BiLSTMs, and
transformer-based BERT and XLNET were used to train and evaluate the model, with the number of epochs varied. Based on experimental results, the unified feature representation model captures both the semantic and structural properties of text, outperforming baseline models by 2%-15%, enabling more effective learning across heterogeneous domains. Unlike prior syntax-aware
transformer models that inject grammatical structure through additional
attention layers, tree encoders, or full fine-tuning, the proposed framework treats grammar as an explicit inductive bias rather than a learnable module, resulting in a very lightweight model that delivers better performance on edge devices
Read the full abstract ▾
Computation and Language
Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization
Gabriel Loiseau, Damien Sileo, Damien Riquet et al. (+2 more)
Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between
privacy protection and utility preservation varies with the data domain,
privacy objectives, and downstream application. However, existing anonymization methods rely on static, manually designed strategies that lack the flexibility to adjust to diverse requirements and often fail to generalize across domains. We introduce adaptive text anonymization, a new task formulation in which anonymization strategies are automatically adapted to specific
privacy-utility requirements. We propose a framework for task-specific
prompt optimization that automatically constructs anonymization instructions for
language models, enabling adaptation to different
privacy goals, domains, and downstream usage patterns. To evaluate our approach, we present a
benchmark spanning five
datasets with diverse domains,
privacy constraints, and utility objectives. Across all evaluated settings, our framework consistently achieves a better
privacy-utility trade-off than existing baselines, while remaining computationally efficient and effective on open-source
language models, with performance comparable to larger closed-source models. Additionally, we show that our method can discover novel anonymization strategies that explore different points along the
privacy-utility trade-off frontier.
Read the full abstract ▾
All authors Gabriel Loiseau, Damien Sileo, Damien Riquet, Maxime Meyer, Marc Tommasi
Computation and Language · Cross-listed from cs.IR
RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition
Kun Ran, Marwah Alaofi, Danula Hettiachchi et al. (+9 more)
This paper presents the award-winning RMIT-ADM+S system for the Text-to-Text track of the NeurIPS~2025 MMU-RAG Competition. We introduce Routing-to-RAG (R2RAG), a research-focused
retrieval-augmented generation (RAG) architecture composed of lightweight components that dynamically adapt the
retrieval strategy based on inferred query complexity and evidence sufficiency. The system uses smaller LLMs, enabling operation on a single consumer-grade GPU while supporting complex research tasks. It builds on the G-RAG system, winner of the ACM~SIGIR~2025 LiveRAG Challenge, and extends it with modules informed by qualitative review of outputs. R2RAG won the Best Dynamic Evaluation award in the Open Source category, demonstrating high effectiveness with careful design and efficient use of resources.
Read the full abstract ▾
All authors Kun Ran, Marwah Alaofi, Danula Hettiachchi, Chenglong Ma, Khoi Nguyen Dinh Anh, Khoi Vo Nguyen, Sachin Pathiyan Cherumanal, Lida Rashidi, Falk Scholer, Damiano Spina, Shuoqi Sun, Oleg Zendel
Computation and Language
ID-LoRA: Efficient Low-Rank Adaptation Inspired by Matrix Interpolative Decomposition
Xindian Ma, Rundong Kong, Peng Zhang et al. (+2 more)
LoRA has become a universal Parameter-Efficient Fine-Tuning (PEFT) technique that equips Large
Language Models (LLMs) to adapt quickly to new tasks. However, when these models are scaled up, even the latest LoRA variants still introduce considerable overhead in trainable parameters. Conversely, aggressively lowering the rank to curb this overhead markedly degrades performance in complex multi-task settings. We propose ID-LoRA, a novel PEFT framework that breaks the trade-off. Its core innovation lies in extracting and reusing clustered parameter groups from the pretrained weight
matrix. These groups are then used to form multiple low-rank components, all of which share only a single initialized trainable low-rank
matrix. This approach cuts the number of trainable parameters while keeping the model's capacity intact. We evaluate ID-LoRA on five diverse
benchmarks: Mathematical
Reasoning, Code Generation, MMLU, CommonsenseQA, and Safety
Alignment. ID-LoRA outperforms both full fine-tuning and existing PEFT baselines (e.g., LoRA, DoRA, HydraLoRA) while using up to 46% fewer trainable parameters than the standard LoRA. In multi-task scenarios, it surpasses LoRA and its recent variants (e.g., DoRA and HydraLoRA) on both Code and MMLU tasks, yet requires only 54% of the trainable parameters demanded by the conventional LoRA.
Read the full abstract ▾
All authors Xindian Ma, Rundong Kong, Peng Zhang, Ruoxiang Huang, Yongyu Jiang
Computation and Language · Cross-listed from cs.AI
Counterfactual Simulation Training for Chain-of-Thought Faithfulness
Peter Hase and Christopher Potts
Inspecting Chain-of-Thought
reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit what insights can be gained from this practice. In this paper, we introduce a training method called Counterfactual Simulation Training (CST), which aims to improve CoT faithfulness by rewarding CoTs that enable a simulator to accurately predict a model's outputs over counterfactual inputs. We apply CST in two settings: (1) CoT monitoring with cue-based counterfactuals, to detect when models rely on spurious features, reward hack, or are sycophantic, and (2) counterfactual simulation over generic model-based counterfactuals, to encourage models to produce more faithful, generalizable
reasoning in the CoT. Experiments with models up to 235B parameters show that CST can substantially improve monitor accuracy on cue-based counterfactuals (by 35 accuracy points) as well as simulatability over generic counterfactuals (by 2 points). We further show that: (1) CST outperforms prompting baselines, (2) rewriting unfaithful CoTs with an LLM is 5x more efficient than RL alone, (3) faithfulness improvements do not generalize to dissuading cues (as opposed to persuading cues), and (4) larger models do not show more faithful CoT out of the box, but they do benefit more from CST. These results suggest that CST can improve CoT faithfulness in general, with promising applications for CoT monitoring. Code for experiments in this paper is available at https://github.com/peterbhase/counterfactual-simulation-training
Read the full abstract ▾
Computation and Language
CAMEL: Confidence-Gated Reflection for Reward Modeling
Zirui Zhu, Hailun Xu, Yang Luo et al. (+4 more)
Reward models play a fundamental role in aligning large
language models with human preferences. Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and generative judging models, which offer richer
reasoning at the cost of higher computational overhead. We observe that the log-probability margin between verdict
tokens strongly correlates with prediction correctness, providing a reliable proxy for instance difficulty without additional inference cost. Building on this insight, we propose CAMEL, a confidence-gated reflection framework that performs a lightweight single-
token preference decision first and selectively invokes reflection only for low-confidence instances. To induce effective self-correction, we train the model via reinforcement learning with counterfactual prefix augmentation, which exposes the model to diverse initial verdicts and encourages genuine revision. Empirically, CAMEL achieves state-of-the-art performance on three widely used reward-model
benchmarks with 82.9% average accuracy, surpassing the best prior model by 3.2% and outperforming 70B-parameter models using only 14B parameters, while establishing a strictly better accuracy-efficiency Pareto frontier.
Read the full abstract ▾
All authors Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar, Kun Xu, Yang You
Computation and Language
CARE: An Explainable Computational Framework for Assessing Client-Perceived Therapeutic Alliance Using Large Language Models
Anqi Li, Chenxiao Wang, Yu Lu et al. (+3 more)
Client perceptions of the therapeutic alliance are critical for counseling effectiveness. Accurately capturing these perceptions remains challenging, as traditional post-session questionnaires are burdensome and often delayed, while existing computational approaches produce coarse scores, lack interpretable rationales, and fail to model holistic session context. We present CARE, an LLM-based framework to automatically predict multi-dimensional alliance scores and generate interpretable rationales from counseling transcripts. Built on the CounselingWAI
dataset and enriched with 9,516 expert-curated rationales, CARE is fine-tuned using rationale-augmented supervision with the LLaMA-3.1-8B-Instruct backbone. Experiments show that CARE outperforms leading LLMs and substantially reduces the gap between counselor evaluations and client-perceived alliance, achieving over 70% higher Pearson correlation with client ratings. Rationale-augmented supervision further improves predictive accuracy. CARE also produces high-quality, contextually grounded rationales, validated by both automatic and human evaluations. Applied to real-world Chinese online counseling sessions, CARE uncovers common alliance-building challenges, illustrates how interaction patterns shape alliance development, and provides actionable insights, demonstrating its potential as an AI-assisted tool for supporting mental health care.
Read the full abstract ▾
All authors Anqi Li, Chenxiao Wang, Yu Lu, Renjun Xu, Lizhi Ma, Zhenzhong Lan
Computation and Language
Semantic Novelty at Scale: Narrative Shape Taxonomy and Readership Prediction in 28,606 Books
W. Frederick Zimmerman
I introduce semantic novelty–cosine distance between each paragraph's sentence
embedding and the running centroid of all preceding paragraphs–as an information-theoretic measure of narrative structure at corpus scale. Applying it to 28,606 books in PG19 (pre-1920 English literature), I compute paragraph-level novelty curves using 768-dimensional SBERT
embeddings, then reduce each to a 16-segment Piecewise Aggregate Approximation (PAA). Ward-linkage clustering on PAA vectors reveals eight canonical narrative shape archetypes, from Steep Descent (rapid convergence) to Steep Ascent (escalating unpredictability). Volume–variance of the novelty trajectory–is the strongest length-independent predictor of readership (partial rho = 0.32), followed by speed (rho = 0.19) and Terminal/Initial ratio (rho = 0.19). Circuitousness shows strong raw correlation (rho = 0.41) but is 93 percent correlated with length; after control, partial rho drops to 0.11–demonstrating that naive correlations in corpus studies can be dominated by length confounds. Genre strongly constrains narrative shape (chi squared = 2121.6, p < 10 to the power negative 242), with fiction maintaining plateau profiles while nonfiction front-loads information. Historical analysis shows books became progressively more predictable between 1840 and 1910 (T/I ratio trend r = negative 0.74, p = 0.037). SAX analysis reveals 85 percent signature uniqueness, suggesting each book traces a nearly unique path through semantic space. These findings demonstrate that information-density dynamics, distinct from sentiment or topic, constitute a fundamental dimension of narrative structure with measurable consequences for reader engagement.
Dataset: https://huggingface.co/
datasets/wfzimmerman/pg19-semantic-novelty
Read the full abstract ▾
Computation and Language
Enhancing Hate Speech Detection on Social Media: A Comparative Analysis of Machine Learning Models and Text Transformation Approaches
Saurabh Mishra, Shivani Thakur and Radhika Mamidi
The proliferation of hate
speech on social media platforms has necessitated the development of effective detection and moderation tools. This study evaluates the efficacy of various machine learning models in identifying hate
speech and offensive
language and investigates the potential of text transformation techniques to neutralize such content. We compare traditional models like CNNs and LSTMs with advanced neural network models such as BERT and its derivatives, alongside exploring hybrid models that combine different architectural features. Our results indicate that while advanced models like BERT show superior accuracy due to their deep contextual understanding, hybrid models exhibit improved capabilities in certain scenarios. Furthermore, we introduce innovative text transformation approaches that convert negative expressions into neutral ones, thereby potentially mitigating the impact of harmful content. The implications of these findings are discussed, highlighting the strengths and limitations of current technologies and proposing future directions for more robust hate
speech detection systems.
Read the full abstract ▾