Computation and Language · Cross-listed from cs.AI
Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Study
Thanh Luong Tuan
Regulated financial institutions operating under data-residency rules need tenant-owned
language models that can run inside the institution's perimeter. This paper combines two related FAOS studies into one mechanism-and-control article. First, it reports a reduced-power proof-of-mechanism study of ontology-amplified
distillation: a Qwen3.6-27B student is adapted to the Foundation AgenticOS ontology through supervised fine-tuning on frontier-teacher trajectories and ontology-grounded direct preference optimization (DPO), trained locally on a single Apple M5 Max from 47 synthetic, English-
language, cross-domain preference pairs. On 40 held-out Vietnamese financial-domain tasks, the distilled student grounds 36 of 40 tasks (grounded rate 0.90; mean ontology term-coverage r_onto = 0.95 on a metric floored at 0.50), equal to the GPT-5 frontier baseline, which also grounds 36 of 40. The outcome is underpowered to establish equivalence: the paired-difference 95% confidence interval spans +/-4 tasks, and the run does not test or show the pre-registered amplification prediction that the student should exceed the frontier. Second, the paper consolidates a contextuality-audit method for enterprise-
agent routing. In a separate negative-results pilot, the corrected canonical Contextuality-by-Default degree is zero for all Phase 1.3 groups in both the local-Qwen run and an explicitly labeled Gemma replication check; the useful signal is direct influence and construct coupling, not surviving residual contextuality. Together, the studies pair an ontology-grounded model-building mechanism with a governance diagnostic for deciding when apparent disagreement should trigger
prompt standardization, multi-
agent synthesis, or human review. The evidence supports neither deployability, safety, superiority, statistical equivalence, nor a contextuality-positive routing rule.
Read the full abstract ▾
Computation and Language
Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification
Pravina Mylvaganam, Ting Dang, Eliathamby Ambikairajah et al. (+2 more)
Language identification is an important step toward integrating endangered Australian Aboriginal
languages (AALs) into
speech technologies supporting
language revitalisation and digital inclusion. However, extreme data scarcity limits model performance. Transfer learning from high-resource
languages shows promise but often suffers from catastrophic forgetting when adapting to new
languages. Continual learning (CL) can mitigate this issue, though it remains challenging with very limited data. To address this, we propose two hybrid continual learning methods: Replay Augmented Elastic Weight Consolidation and Constraint Guided Knowledge
Distillation to adapt pretrained
speech models for AAL identification while preserving previously learned knowledge. Experiments on Warlpiri, Dalabon and Dharawal show that the proposed methods outperform fine-tuning and existing CL baselines, improving adaptation to multiple AALs while maintaining performance on previously learnt high-resource
languages.
Read the full abstract ▾
All authors Pravina Mylvaganam, Ting Dang, Eliathamby Ambikairajah, Vidhyasaharan Sethu, Jingyao Wu
Computation and Language
Belief-reality separation lives in routing over a shared value slot in language models
Oliver Steele, Jiangtao Wen and Yuxing Han
Capable
language models hold what a character believes apart from what is true: told "Anna believes the cup is blue; in reality it is red," they answer blue about Anna and red about the world. Where in the computation does that separation live? We show it rests on two separable mechanisms at two positions. A generic value slot binds the attributed value. A router at the query position selects which frame, the character's belief or reality, a query reads out. Two routes fill the slot: an asserted belief, whose value the text supplies, binds in directly; a derived belief, whose value must be inferred from what the character could see, arrives by a visibility-gated lookback. A subspace trained on either route steers the other, and only the derived route depends on described visibility. The slot itself carries no belief-reality tag: intervening on it moves a reality readout as strongly as a belief one. The separation lives instead in a dissociated pair of routing subspaces, which flip a query between frames without injecting the donor's value. These results hold across three architectures, on stimuli de-confounded against theory-of-mind-
benchmark shortcuts; the behavior itself emerges between 3B and 7B across five model families. This paper develops the single belief-reality axis in depth; a companion paper shows the same slot-and-router format is shared across the other non-actual contexts a sentence can open (counterfactual, fictional, temporal).
Read the full abstract ▾
Computation and Language
MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization
Prateek Singh
How do different components of iterative
prompt optimization interact, and what happens when they are combined? We investigate this through MAGE (
Memory-Augmented Goal-directed
Prompt Evolution), a controlled analysis framework for studying component interaction in
prompt optimization. MAGE is not proposed as a superior optimizer in absolute terms; it integrates episodic
memory, multi-objective Pareto selection, and adaptive evaluation as a platform for controlled ablation. Our experiments uncover a previously unreported phenomenon, the
Prompt Optimization Coupling Effect (POCE): when multiple
stochastic optimization signals operate within a closed reflective loop, they interact in ways that simultaneously improve performance and amplify variance, behavior that cannot be predicted by analyzing components in isolation. Three main findings emerge. First, failure-grounded reflection is essential: methods relying only on scores (OPRO) or abstract critique (Self-Refine) fail to improve
prompts. Second, MAGE achieves 46.4% versus GEPA's 34.0% on GSM8K-Hard (+12.4%, P(MAGE>GEPA)=0.998, 5 seeds on gpt-4o-mini), with comparable variance (7.3% vs. 7.0%). Third, increasing candidate diversity reveals the clearest POCE signal: expanding the candidate pool from n=3 to n=5 improves mean accuracy by +21.6% while increasing variance by 3.7x. We further validate on Llama 3.1 8B and show POCE is headroom-dependent: when the base model already achieves high accuracy, variance amplification disappears. Finally, in low-data regimes (Ntrain=30), well-designed fixed
prompts outperform all reflective optimizers, indicating that scaffold choice dominates optimizer choice. Our results suggest
prompt optimization systems behave as coupled
stochastic processes and should be evaluated in terms of both performance and stability, not just peak accuracy.
Read the full abstract ▾
Computation and Language
Transforming LLMs into Efficient Cross-Encoders via Knowledge Distillation for RAG Reranking
Shreeya Dasa Lakshminath and Shubhan S
Cross-encoders achieve high reranking accuracy in
Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment. We address this by fine-tuning LLaMA 3 (8B) as a drop-in reranker using a two-stage pipeline: supervised fine-tuning on a custom query-document relevance
dataset via the Unsloth framework with LoRA adapters, followed by 4-bit quantization for efficient inference. The resulting model replaces the cross-encoder in a dual-retriever RAG pipeline combining BM25 and dense vector search. Evaluated on a domain-specific question-answering
benchmark using the RAGAS framework, our fine-tuned LLaMA 3 reranker achieves gains of 14% in answer relevancy, 16% in context precision, 19% in answer similarity, and 21% in answer correctness over the cross-encoder baseline, while reducing inference overhead through 4-bit quantization. These results demonstrate that instruction-tuned LLMs can be adapted into accurate, efficient rerankers without the quadratic complexity of traditional cross-encoders.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
Kexin Huang, Junkang Wu, Jinda Lu et al. (+7 more)
Reinforcement learning (RL) has significantly enhanced the
reasoning capabilities of large
language models (LLMs), yet the training process remains notoriously fragile. In this work, we investigate a critical source of this instability: over-optimization, where models exploit training heuristics at the expense of generalizable
reasoning. While reverse KL regularization is the standard defense against such degradation, our analysis reveals that it is often insufficient in this regime, as it fails to ensure comprehensive coverage of the reference distribution. To address this, we propose ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization. ARMOR comprises two key components: (1) Anchor Rollout, which leverages off-policy data from the reference policy to preserve established solution patterns; and (2) Mixed Optimization, which reformulates the policy objective to enable controlled exploration without relying on auxiliary losses. Extensive experiments on
reasoning benchmarks validate that ARMOR effectively mitigates validation collapse, enabling sustained performance improvements over extended training horizons.
Read the full abstract ▾
All authors Kexin Huang, Junkang Wu, Jinda Lu, Shuo Yang, Chiyu Ma, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou
Computation and Language
When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation
Lekang Jiang, Wenjun Sun and Stephan Goetz
Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the
reasoning capabilities of large
language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that
reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where
reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized
reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications.
Read the full abstract ▾
Computation and Language
Hallucination Detection in Large Language Models Using Diversion Decoding
Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed et al. (+4 more)
Large
language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit
hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate LLM uncertainty and detect
hallucinations. However, existing approaches are often probabilistic and computationally expensive, limiting their practical applicability. In this paper, we introduce diversion decoding, a novel method for developing an LLM uncertainty heuristic by actively challenging model-generated responses during the decoding phase. Through diversion decoding, we extract features that capture the LLM's resistance to produce alternative answers and utilize these features to train a machine-learning model to develop a heuristic measure of the LLM's uncertainty. Our experimental results demonstrate that diversion decoding outperforms existing methods with significantly lower computational complexity, making it an efficient and robust solution for evaluating
hallucination detection.
Read the full abstract ▾
All authors Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed, Anoop Singhal, Latifur Khan, Punya Parag Modi, Ehab Al-Shaer
Computation and Language · Cross-listed from cs.CV
Not All Color Categories Are Equally Stable: A Multilingual Free Color Naming Experiment
Nuray Toganas, Adilet Yerkin, Elnara Kadyrgali et al. (+3 more)
Color naming is an important part of human color perception. Its task is to allow people to describe continuous colors using discrete color categories. However, the boundaries between color categories are often unclear, and some colors may be perceived differently depending on their saturation and brightness. While certain color categories remain recognizable across a wide range of shades, others may be associated with different color names when their appearance changes. This study investigates the consistency of color naming for red, yellow, and green color categories using a free color-naming experiment. A set of 18 color samples was selected from the COLIBRI
dataset to represent different shades of these colors. Participants (n = 92) were asked to freely assign color names to each sample in Kazakh, Russian, or English without being limited to predefined categories. The results show that color categories differ in their consistency. Green shades were consistently identified as green despite variations in appearance, whereas yellow shades received a wider variety of names, including gold- and brown-related descriptions. Red shades showed moderate naming consistency. Our findings suggest that some color categories occupy broader perceptual regions than others and may therefore be more robust to visual variations. The study results can be used to develop perceptually meaningful color models and color naming systems.
Read the full abstract ▾
All authors Nuray Toganas, Adilet Yerkin, Elnara Kadyrgali, Muragul Muratbekova, Aron Karatayev, Pakizar Shamoi
Computation and Language · Cross-listed from cs.AI
ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
Kefan Song and Yanjun Qi
Autonomous CLI
agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight. Does greater autonomy invite greater risk? We introduce ANCHOR, an automated
auditing framework that stress-tests CLI
agents on illegal tasks grounded in public US court cases. ANCHOR deploys an auditor
agent fine-tuned on dark personality data using supervised and reinforcement fine tuning. This auditor roleplays persistent malicious users who decompose tasks, reframe requests upon refusal, and adapt strategies across multi-turn interactions. Evaluating frontier CLI
agents, we find that while they often refuse illegal tasks when prompted directly, compliance reaches 100% under persistent malicious interaction. When
agents comply, they frequently exceed user requests, autonomously building infrastructure for large-scale harm, including catastrophic risk scenarios such as large-scale financial fraud and bioweapon development. These findings demonstrate that current
alignment techniques are insufficient for autonomous
agents and underscore the need for safety evaluations against persistent, adaptive malicious users. We release ANCHOR at https://github.com/garified/anchor
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams
Siddharth Pal and Viktoria Rojkova
Context engineering decides what information a model carries forward, and current designs meter it in
tokens: compressing the past into a bounded recurrent state, keeping a key-value entry for every
token, or imposing a fixed budget through a window or eviction rule. All three make the
token the unit of
memory even when the stream is redundant and the task depends on the distinct information it carries. Building on a companion mechanism paper that opens a cache slot only when an incoming key is novel, so
memory scales with the number of distinct items rather than
tokens, we develop that allocate-on-novelty cache as a working-
memory component and organize context by how a task depends on the past: recall-carried information belongs in a content-addressed novelty cache, summary-carried information in a recurrent state, and locality-carried information in a recency window. The claim is empirical and bounded. On a matched character-level control, novelty-gated
attention reaches full-
attention performance while attending to about half the
tokens, and coupling the cache with a state-space summary matches full-
attention coupling at that reduced cost; the advantage grows as context lengthens, while a sliding window is preferable on short, locality-dominated spans. On next-code prediction over synthetic Medicare claims the coupled component leads full
attention and every fixed-budget eviction policy at a thousand-event horizon, whereas cost
forecasting over the same stream is summary-carried and the cache is neutral. The retained
memory is an inspectable table of templates, codes, drugs, or places rather than an opaque state. The experiments are small-scale and use only public data; they establish the primitive that context can scale with distinct information rather than
tokens, in a working
memory that is content-addressable and auditable.
Read the full abstract ▾
Computation and Language
Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging
Jinglan Gong, Jiefan Lu, Hewei Guo et al. (+5 more)
Evaluating large
language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn
benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion across many turns. We introduce EYT-Bench, a human-centered
benchmark whose evaluation protocol is built around a decoupled three-party design: a persona-grounded user simulator, a target model evaluated on both intent perception and response generation, and an independent, configurable ensemble of LLM judges. Across 3,400 dialogues with 17 target models, EYT-Bench reveals four findings that previous
benchmarks miss: (i) state-of-the-art closed and open-source models are statistically indistinguishable on subjective dimensions, but separate by up to 9x on objective intent-tracking; (ii)
reasoning is a phase transition for objective tracking on long-context personas but is essentially flat on subjective scores; (iii) persona format strongly affects trajectory spread, FICR (final-intent completion rate) saturates above 0.95 on Nemotron-USA but ranges from 0.53 to 0.88 on PersonaMem-v2; and (iv) the warm-up effect is observed in 16 of 17 models.
Read the full abstract ▾
All authors Jinglan Gong, Jiefan Lu, Hewei Guo, Kehan Li, Zhiyuan Han, Jihang Jiang, Wenwen Tong, Lewei Lu
Computation and Language
A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization
Lingyun Shen and Xuejia Guo
Although large
language models (LLMs) have shown promising potential in news summarization tasks, their performance on long-document summarization remains challenging as their length often exceeds the input limits. As the
agent investment, which provide possibility to improve the inherent capabilities of LLMs. To enhance the effectiveness of long-document summarization based on LLMs, this paper proposes an expert-editor stepwise questioning multi-
agent method, in which the expert and the editor guide another
agent to refine the summary by posing questions on different aspects of the content and providing targeted clues for revision. We conducted experiments on two representative long-document scientific
datasets and evaluated the results through widely recognized automatic metrics. The results demonstrated the effectiveness of our method.
Read the full abstract ▾
Computation and Language · Cross-listed from eess.AS
GigaChat Audio: Time-aware Large Audio Language Model
Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov et al. (+4 more)
Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio
tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long
benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture design affect accuracy and computational cost. We release model weights and
datasets to support further research on time-aware audio understanding, available at https://huggingface.co/ai-sage/GigaChat3.1-Audio-10B-A1.8B.
Read the full abstract ▾
All authors Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov, Alexandr Maximenko, Oleg Kutuzov, Pavel Bogomolov, Fyodor Minkin
Computation and Language
Structured Thoughts For Improved Reasoning And Context Pruning
Zain Sarwar, Supriyo Chakraborty, Berkcan Kapusuzoglu et al. (+5 more)
Large
language models (LLMs) excel at generating long chains of thought, but long
reasoning traces are often verbose and
memory-inefficient. In this work, we introduce Structured Thoughts, a framework that organizes
reasoning into alternating <try> and <outcome> blocks: <try> captures exploratory scratch work, while <outcome> contains the distilled conclusion of that step. We construct a
dataset of structured thoughts by segmenting
reasoning traces into <try> blocks and prompting an LLM to summarize each step into its corresponding <outcome>. Fine-tuning pretrained foundation models on this reformatted data produces models that adopt the structured
reasoning style, leading to performance gains of up to 8.08% on
reasoning benchmarks compared to standard SFT. The explicit structure also enables context
pruning: after each <try>/<outcome> pair, the <try> can be pruned, allowing the model to retain conclusions without keeping the full scratch work in the context. A proof-of-concept
pruning implementation achieves an average of 85%
memory / context savings with an 8.67% performance drop across mathematical tasks.
Read the full abstract ▾
All authors Zain Sarwar, Supriyo Chakraborty, Berkcan Kapusuzoglu, Chia-Hsuan Lee, Anirban Das, Stephen Rawls, Kartik Balasubramaniam, Sambit Sahu
Computation and Language
CAFE: A Compound-AI Factorial Evaluation Framework
Fabian Lukassen, Christoph Weisser, Thomas Kneib et al. (+1 more)
We introduce CAFE (Compound-AI Factorial Evaluation), an open-source platform that brings design of experiments to the evaluation of compound AI systems (CAIS). Such systems expose many interchangeable choices - e.g. which retriever, model, or
prompt - and practitioners rarely know which of them most affects answer quality. With CAFE, a practitioner registers each swappable component of a pipeline as a factor to build a factorial design over the chosen factors, run the resulting configurations, and score the answers on a shared rubric using a configurable LLM judge together with human raters. From these ratings it attributes answer-quality variance to the components and their interactions with mixed-effects models and reports effect sizes, significance, the best configuration, cost and latency trade-offs, and judge-human reliability. Whereas existing tools mostly either search for a good configuration or score outputs in isolation, CAFE also explains which component drives quality and whether an observed difference is significant. We validate CAFE on a
retrieval-augmented question-answering (QA) pipeline over the HotpotQA
benchmark dataset, where it recovers planted factor effects and stays calibrated under a permutation null. CAFE is released as a Python package and as a Web application.
Read the full abstract ▾
All authors Fabian Lukassen, Christoph Weisser, Thomas Kneib, Alexander Silbersdorff
Computation and Language · Cross-listed from eess.AS
GigaAM Multilingual: Foundation Model for Underrepresented Languages
Andrei Kuzmenko, Alexandr Maximenko, Aleksandr Kutsakov et al. (+5 more)
Despite recent scaling successes,
multilingual ASR performance remains highly uneven, with long-tail
languages suffering from severe data scarcity. This work addresses the challenge of building robust foundation models for underrepresented Central Asian
languages (Kazakh, Kyrgyz, Uzbek). We present GigaAM
Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective. Crucially, we introduce a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-
language dominance. In controlled comparisons, our approach outperforms strong open pretrained encoders (Whisper Large v3, Omnilingual-1B) on target
languages, achieving significant gains on spontaneous
speech while maintaining efficiency. We release the foundation encoder and ASR model, offering a proven recipe for effective
multilingual adaptation under realistic data imbalance.
Read the full abstract ▾
All authors Andrei Kuzmenko, Alexandr Maximenko, Aleksandr Kutsakov, Georgii Gospodinov, Dmitrii Bolotov, Oleg Kutuzov, Pavel Bogomolov, Fyodor Minkin
Computation and Language · Cross-listed from cs.SD
PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditions
Zhenshan Zhang, Xueping Zhang, Linxi Li et al. (+2 more)
Recent studies on partial audio spoofing mainly focus on studio-recorded
speech with temporal localization of spoofed segments. However, these studies often overlook realistic conditions where spoofed and bonafide segments simultaneously coexist across
speech and environmental sound components. In this paper, we present PC-Mix, the first
dataset for partial-component spoofing detection, where either or both audio components may be partially spoofed. In PC-Mix, bonafide and partially spoofed environmental-sound components are first constructed and mixed with
speech signals from an existing partial-spoof
dataset, producing audio in which either or both components may be locally manipulated. This design addresses two major gaps in existing partial spoofing
benchmarks: the lack of realistic environmental sounds in
speech partial spoofing scenarios and the absence of partial spoofing detection for environmental sound components. We further establish standardized evaluation protocols and design a joint learning framework to optimize spoofing detection across
speech, environmental sound, and mixed audio. Experiments highlight the increased difficulty introduced by mixed conditions. The results demonstrate that training under matched target conditions is more effective than directly transferring models trained on
speech or environmental sound components.
Read the full abstract ▾
All authors Zhenshan Zhang, Xueping Zhang, Linxi Li, Yechen Wang, Ming Li
Computation and Language
Neutralizing Structural Inequality in the Nigerian FinTech Sector
Muhammad Abdullahi Said
Algorithmic decision systems in financial services often rely on data proxies that inadvertently encode structural inequalities. This paper introduces a hierarchical human-AI triage model for Point of Sale fraud detection in the Nigerian FinTech sector. Adopting a We Are All Equal worldview, we address the challenge of discrimination laundering, wherein the system misinterprets infrastructure related aleatoric noise such as rural network timeouts as fraudulent intent. We implement a three-tier routing policy utilizing a calibrated ensemble model as a primary filter. The policy routes transactions characterized by epistemic uncertainty such as cold start new accounts to specialist analysts while reserving high stakes cases for a senior supervisor. To manage finite human capacity, we utilize a dynamic shadow price to ration human
attention and implement a random audit mechanism to prevent human skill atrophy. Our experimental results demonstrate a statistically significant 1.88% complementarity gap and a 24.79% percentage point gain in fraud recall over an autonomous baseline. Crucially, the model reduces the regional performance gap from 19.43 to 2.88 percentage points, neutralizing structural bias. Hierarchical collaboration provides a robust mechanism for substantive equality of opportunity, ensuring that rural accounts are not excluded from the digital economy due to environmental brute luck.
Read the full abstract ▾
Computation and Language
Polarization Detection: A Hybrid Approach with AfroXLMR-Social and DeBERTa for Low- and High-Resource Settings
Muhammad Abdullahi Said
The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts. This paper presents our system description for the POLAR Shared Task 2026, focusing on the detection and characterization of polarized discourse in English and Hausa. We propose a hybrid modeling strategy: for English binary detection, we leverage the monolingual strength of DeBERTa, while for Hausa and all fine-grained subtasks (Types and Manifestations), we utilize AfroXLMR-Social. This domain-adapted
multilingual model proved critical for capturing the nuances of polarization in social media text. To further address computational constraints and data scarcity, we implement Low-Rank Adaptation (LoRA) and textual data augmentation via nlpaug. We report competitive results across all three subtasks, demonstrating that model selection tailored to specific subtask requirements yields the best balance of performance.
Read the full abstract ▾
Computation and Language
PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment
Zhiyuan Wen, Jiannong Cao, Kelly Chan et al. (+5 more)
Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLM-based platform for immersive mock interview practice with comprehensive
multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware follow-up questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggregated into 10 assessment aspects and two competency tracks. Guided by the KSA and
STAR frameworks, the report links each score to behavioral evidence and actionable recommendations. PolyInterview is publicly accessible. Its current all-account snapshot contains 101 accounts, 1,564 interview sessions, 7,665 generated questions, and 1,422 five-stage question sets. Generated questions are more closely aligned with their matched job description than with cross-role job descriptions in 93.7% of sessions. An evaluation by ten experts found strong question plans and actionable feedback.
Read the full abstract ▾
All authors Zhiyuan Wen, Jiannong Cao, Kelly Chan, Zijian Wang, Chen Chen, Xiaoyun Liu, Jianing Yin, Zhuo Li
Computation and Language · Cross-listed from cs.CV
ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing
Jiakang Yu, Yixuan Chai, Tianci Wang et al. (+7 more)
Generative image editing models struggle with structured statistical charts when data modifications require
geometric synchronization. We formalize this task as Visuo-Logical Cascading Editing (VLCE). However, existing methods remain confined to localized text substitutions and struggle with dependency-aware cascading updates. To systematically evaluate this capability, we introduce ChartSync, an expert-validated
benchmark constructed via a programmatic rendering pipeline that guarantees deterministic visuo-logical coupling for the ground truth. ChartSync comprises 870 triplets across 9 chart categories and 4 task types, including 235 geometry-coupled VLCE instances that specifically test cascading text-to-geometry synchronization. We further evaluate these instances via a two-tier framework combining objective visual metrics with a
vision-
language model judge paradigm to assess low-level fidelity alongside
multimodal comprehension and
reasoning. Evaluating 14 image editing models and one code-mediated pipeline reveals a nuanced capability gap: most open-source models suffer severe drops in
geometric synchronization, while only two frontier proprietary models show emerging VLCE capability, with their residual errors mainly involving semantic isolation and background corruption. Our detailed error analysis deconstructs these failure paradigms to identify core meta-abilities for guiding future
multimodal architectures. The ChartSync
dataset and code are publicly released at https://github.com/kaka-yjk/ChartSyncCodebase.
Read the full abstract ▾
All authors Jiakang Yu, Yixuan Chai, Tianci Wang, Rihui Jin, Guangkai Xu, Hongtao Deng, Xun Zhu, Wang Gao, Xinrun Guo, Haipang Wu
Computation and Language · Cross-listed from cs.AI
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
Dongxu Zhang, Yiding Sun, Zihao Guo et al. (+5 more)
Reasoning failures in large
language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may reflect missing capability, an unstable
reasoning trajectory, or a failure to activate a
reasoning state that is already available in the frozen model. Existing prompting and
benchmark-based evaluation methods mostly operate at the output level, while generic activation-steering methods typically apply global directions without diagnosing which examples require intervention. In this paper, we introduce SPARK, which uses hidden-state response to diagnose whether a model internally enters an effective
reasoning state and to guide lightweight test-time steering. The key observation is that raw hidden-state susceptibility is strongly confounded by
prompt length, especially in programmatic and algorithmic
reasoning where harder serialized instances naturally become longer. SPARK therefore uses length-controlled susceptibility to separate input-scale effects from residual
reasoning activation, and combines this signal with cross-layer coordination to select
reasoning-active anchors and under-activated hard examples. We use FRONTIER-4.5K as a controlled programmatic
reasoning suite for latent profiling and difficulty-aware analysis, and evaluate SPARK-Steering on GSM8K and MATH-500 with forward-only
benchmark profiling. Our method improves Qwen3 series models consistently; on MATH-500, accuracy rises from 82.0% to 84.6% for Qwen3-4B and from 82.4% to 85.6% for Qwen3-8B. These results suggest that susceptibility can serve not only as a diagnostic signal for
reasoning failures, but also as a practical guide for targeted test-time intervention.
Read the full abstract ▾
All authors Dongxu Zhang, Yiding Sun, Zihao Guo, Xiangyang Yang, Kai Tang, Lin Chen, Cheng Tan, Jihua Zhu
Computation and Language · Cross-listed from cs.AI
Information-seeking failures of large language models in agentic clinical reasoning
Krischan Braitsch, Laura K. Schmalbrock, Theresa Weltermann et al. (+11 more)
Large
language models achieve high scores on medical knowledge assessments, yet clinical
reasoning requires actively deciding what to investigate under uncertainty. We developed an agentic evaluation framework in hematologic oncology in which models must proactively request clinical data across three sequential rounds before committing to a diagnosis and treatment plan. Across 32 frontier models, the best achieved only 68% overall accuracy. Information utilization, the fraction of available data actually requested, was the strongest predictor of diagnostic accuracy (R = 0.69, P < 0.001), yet utilization collapsed from 57% to 26% in the final round, leaving molecular and cytogenetic data critical for treatment selection unexamined.
Reasoning traces scored high on a clinical
reasoning rubric (91% above threshold) but decorrelated from accuracy, revealing a gap between locally coherent rationales and globally correct conclusions. Error analysis identified search satisficing, anchoring and premature closure as the dominant failure modes, the same cognitive biases that characterize novice clinicians under dual-process models of diagnostic
reasoning. These findings demonstrate that the primary limitation of current models in clinical oncology is not insufficient medical knowledge but a systematic failure of information-seeking under uncertainty.
Read the full abstract ▾
All authors Krischan Braitsch, Laura K. Schmalbrock, Theresa Weltermann, Andrew F. Berdel, Isabella Miller, Kai Tran, Michael Heider, Sabrina Kraus, Florian Bassermann, Jacqueline Lammert, Sebastian Ziegelmayer, Marcus Makowski, Lisa C. Adams, Keno K. Bressem
Computation and Language
Language Re-generation: An investigation into information locality effects on reconstruction
Amirhossein Mohammadi, Laurence E. Frank, Albert Gatt et al. (+1 more)
Information locality, the tendency for syntactically related words to appear close together, shapes both human
language processing and
language model learning. While prior work has examined whether
language models can acquire impossible
languages, it remains unclear whether they can recover natural
language from such input and what this reveals about their inductive biases. We address this by complementing learnability-based approaches with a reconstruction framework: fine-tuning GPT-2 models pre-trained on impossible
languages to reconstruct natural English from three perturbation types. Our findings show that the recovered structures exhibit shorter dependency lengths than the original text, mirroring the locality preference observed in unconstrained
language model generation and providing a quantitative signature of an architectural bias that learnability experiments alone do not reveal. Recovery difficulty increases with the degree of locality disruption. Structural recovery (dependency Triple F1) dissociates from surface recovery (Exact Match), while fluency dissociates from faithful reconstruction under global shuffling. Sentence length further modulates performance: longer sentences facilitate recovery when local structure is preserved but lead to complete collapse under global shuffling. Finally, recovery difficulty tracks learnability difficulty across perturbation types, suggesting that information locality is the shared constraint governing both.
Read the full abstract ▾
All authors Amirhossein Mohammadi, Laurence E. Frank, Albert Gatt, Robert A. Bagheri
Computation and Language
Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASR
Pravina Mylvaganam, Eliathamby Ambikairajah, Ting Dang et al. (+2 more)
This paper investigates how
language similarity can improve cross-lingual transfer for automatic
speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal
language, has very limited transcribed
speech data, making transfer learning essential. We propose a framework combining acoustic similarity from pre-trained
speech models with linguistic similarity based on typology, phoneme inventories, grammatical, and syntactic features to rank high-resource source
languages and evaluate their effectiveness for ASR transfer to Warlpiri. Experiments with Whisper show that acoustically and typologically similar
languages outperform monolingual and
multilingual baselines. Assamese and Hindi achieve substantial reductions in word and character error rates. Correlation analysis further indicates that acoustic similarity is the strongest predictor of fine-tuning performance, while phoneme inventory and typological similarity better explain zero-shot transfer.
Read the full abstract ▾
All authors Pravina Mylvaganam, Eliathamby Ambikairajah, Ting Dang, Vidhyasaharan Sethu, Tuende Szalay
Computation and Language · Cross-listed from cs.CR
One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions
Tomas Bruckner
Large
language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights. Existing identification techniques require long generated texts,
token-level log-probabilities, adversarially crafted
prompts, or the model owner's cooperation. We show that far weaker evidence suffices. We define a behavioral fingerprint of an LLM as the empirical distribution of its answers to trivial one-word
prompts - "name a random number between 1 and 100" - collected across four
languages at a cost of one output
token per query. Measuring 165 models served via a large commercial aggregator (OpenRouter), we find that (i) these distributions are highly non-uniform (median
cell entropy 1.0 bit) and model-specific: split halves of the same model's samples lie an order of magnitude closer than samples of different models; (ii) Jensen-Shannon divergence between fingerprints recovers model lineage, assigning a model to its documented family with 59.5% leave-one-out accuracy against an 18.4% chance rate; and (iii) a biometric-style verification protocol achieves a 7.3% equal error rate with the full 40-
cell battery, and below 11% with eight probe
cells - roughly a hundred single-
token queries per audit. We further report ecosystem anomalies, including a proprietary-branded flagship endpoint distributionally indistinguishable from an open-weight Qwen model. The protocol,
prompts, raw data, and analysis code are released for reproduction and operational use.
Read the full abstract ▾
Computation and Language
One mechanism for many mental spaces: a shared router over a value slot in language models
Oliver Steele, Jiangtao Wen and Yuxing Han
Language builds discourse contexts other than the actual: a painting, a belief, a
memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive). Fauconnier's mental-space theory, by contrast, treats them as one space-building operation. We ask which of these a
transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed
Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families. Belief, which formal semantics marks as a distinct case, is not specially separated. The router is low-rank, composes additively with entity identity, and acts through a few late-layer heads. Two further results show the mechanism drives inference and composes: a subspace trained on a rule-derived conclusion flips what the model infers while dissociating from what it reports, and composing space-builders mints a fresh router over the shared slot. This paper establishes the cross-type generality. A companion paper develops belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports).
Read the full abstract ▾
Computation and Language
PTEI: Integrating Personality Traits to Enhance Emotional Intelligence in Large Language Models
Amir Reza Jafari, Praboda Rajapaksha, Reza Farahbakhsh et al. (+1 more)
Despite advances in Emotional Intelligence (EI), Large
Language Models (LLMs) still significantly underperform humans in complex emotional
reasoning. This gap originates partly from the limited incorporation of individual differences, particularly personality traits, which are fundamental to human emotional inference. To address this, we propose PTEI, a novel framework for integrating Personality Traits into Emotional Intelligence tasks using LLMs. In PTEI, MBTI and OCEAN personality traits are first extracted directly from the given emotional scenarios and then utilized as contextual knowledge within personality-aware
prompts, guiding LLMs to accurately infer
emotions and their underlying causes. To ensure optimal contextual grounding, we employ Contrastive Learning to construct an optimized
retrieval system that surfaces emotionally and personally aligned scenarios, enhancing
reasoning quality. Extensive experiments on established EI
benchmarks show that PTEI enhances the Emotional Understanding (EU) capabilities of various LLMs, with the strongest improvement observed in GPT models. Combining PTEI with Chain-of-Thought (CoT)
reasoning yields an additional 4 percent increase in accuracy. These findings underscore PTEI's contribution toward advancing AI systems with more sophisticated social and psychological grounding.
Read the full abstract ▾
All authors Amir Reza Jafari, Praboda Rajapaksha, Reza Farahbakhsh, Noel Crespi
Computation and Language
Consensus vs. Dissent: Dynamic LLM Modeling of Subjective Preferences in Group Recommenders
Cedric Waterschoot, Nava Tintarev and Francesco Barile
Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of
fairness, satisfaction, and consensus. We do this by fine-tuning Large
Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a
reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the one that maximizes these predicted human-like evaluations. We further validate these suggestions in a user study (n=284) and find that our methodology achieved the highest scores for satisfaction and group consensus. Furthermore, we find that LLM judgments are most aligned with human perceptions of
fairness, satisfaction and consensus when we also consider interaction effects between our LLM-based method and group configuration (e.g., minority or coalition). These findings give further support for dynamically adapting aggregation strategies to specific within-group preference distributions, and highlight the advantage of using LLMs for an adaptation that is aligned with subjective human judgments.
Read the full abstract ▾