Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Saturday 25 July

Computation and Language

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran et al. (+1 more)

Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages. Sanskrit, Tamil, and other classical Indic languages exhibit agglutinative morphology, productive sandhi (phonological fusion at word boundaries), and domain-specific vocabularies absent from general-purpose training data. This paper presents BHARATI, a set of SentencePiece BPE tokenizers trained on a balanced 781 MB corpus spanning seven languages (English, Hindi, Sanskrit, Tamil, Telugu, Kannada, and Malayalam) with native script support for all languages. We describe three successive tokenizer versions: v1 (English and Sanskrit only, with broken byte-fallback for Tamil), v2 (four-language support with byte-level fallback for southern languages), and v3 (full seven-language native subword coverage). Subword fertility analysis demonstrates that v3 averages 2.6 tokens per Indian Knowledge System (IKS) technical term, compared to 5.25 tokens per term with GPT-2's tokenizer and 3.75 tokens with the multilingual SentencePiece baseline, with the largest gains on a set of reserved IKS terms that are represented as single tokens by construction. On a held-out test set of 490 IKS-domain sentences (70 per language across seven languages, released with the measurement script), v3 reduces sequence length by roughly 90% relative to GPT-2 and byte-level encoding (which lack native Indic subwords) and by approximately 25% relative to the mBART-50 multilingual baseline, averaged across the six Indic languages, directly translating to increased effective context length for downstream language models. The tokenizer models (32,000 vocabulary), training scripts, and evaluation benchmarks are released under open licenses.
Read the full abstract

All authors Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran, Santhosh Sivasubramani

Computation and Language

Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering

Hieu Man and Thien Huu Nguyen

Multi-hop question answering requires coordinating relational and textual evidence across reasoning steps, a combination neither a text corpus nor a knowledge graph can supply alone. Prior work often emphasizes only part of this loop: graph-augmented RAG retrieves from a pre-built or query-updated graph, KGQA systems search within topic-centered subgraphs, and memory-augmented agents maintain evolving memories without continuously reconciling graph memory with textual context. We propose Co-E, a training-free system built around synchronized bidirectional graph-text working memory. A synchronization cycle consolidates textual memory, extracts relational triples into graph memory, and injects graph facts back into the generation context. Because both memories are maintained, they shape subsequent retrieval and generation. Evaluated on six multi-hop QA benchmarks, Co-E improves over comparable training-free open-backbone baselines and is competitive with larger or trained systems.
Read the full abstract

Computation and Language

IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages

Sahil Deepak Gawande and Mayank Singh

Large Language Models (LLMs) have transformed conversational AI, yet high-quality multilingual code-mixed dialogue resources remain scarce, particularly for Indic languages where speakers naturally alternate between English and their native language in both native-script and Romanized forms. We present IndicTalk, one of the largest multilingual Indic code-mixed conversational corpora, comprising over 13,28,604 event-grounded multi-turn conversations across 18 language varieties covering 9 Indic languages. The corpus is generated through a fully automated pipeline that combines real-world news grounding, persona-conditioned dialogue generation using multilingual LLMs, and automatic quality validation. Extensive linguistic, automatic, and human evaluations demonstrate that IndicTalk produces fluent, coherent, and naturally code-mixed conversations across both script variants. We will release IndicTalk to support the development and evaluation of multilingual conversational AI for underrepresented Indic languages. The dataset is available at: https://huggingface.co/datasets/LingoIITGN/IndicTalk .
Read the full abstract

Computation and Language · Cross-listed from cs.RO

Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot

Yuki Okafuji, Koji Inoue and Yoshiki Ohira

Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage incremental framework that decouples prefatory-response preparation from speech onset. Once user intent becomes predictable, an intent readiness detector triggers LLM-based generation of a short prefatory response. Concurrently, a voice activity projection (VAP) model determines when to deliver it. Through a field experiment with a route-guidance robot in a shopping mall, we evaluated three conditions: no-filler, fixed-filler, and contextual-preface. Both fixed-filler and contextual-preface significantly reduced initial response latency relative to no-filler. Relative to fixed-filler, contextual-preface had significantly longer initial response latency but a significantly shorter initial-to-main gap. Exploratory ratings showed no significant differences. These results indicate a timing trade-off.
Read the full abstract

Computation and Language

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining

Rares A.C. Diaconescu, Iulia Slanina, Alina Florea et al. (+5 more)

Reducing toxicity is often framed as a global alignment problem, yet perceptions of harmful language are subjective and context-dependent. We present the first comparative evaluation of training-free methods for aligning language generation to user-specific toxicity sensitivities across three inference-time intervention stages: pre-decoding (prompt conditioning and rewriting), in-decoding (token, logit, and representation steering), and post-decoding (candidate re-ranking). Evaluated against toxicity sensitivity targets derived from the PRISM dataset, all methods reduce alignment error by 28-47%. However, the results reveal a fundamental trade-off between alignment effectiveness, personalization, and general language quality, showing how toxicity sensitivity alignment is an inherently multi-objective problem.
Read the full abstract

All authors Rares A.C. Diaconescu, Iulia Slanina, Alina Florea, Andrei B. Trache, Miruna E. Coroi, Anne Arzberger, Jie Yang, Enrico Liscio

Computation and Language · Cross-listed from cs.LG

In-Context Learning as Implicit Policy Gradient

Masahiro Kaneko and Timothy Baldwin

Recent work has shown that large language models (LLMs) can iteratively improve their outputs by incorporating generated samples and their corresponding evaluation scores as in-context examples. Despite these empirical findings, the theoretical foundations underlying this phenomenon remain poorly understood. In this paper, we show that score-conditioned In-Context Learning (ICL) admits a structural correspondence to policy gradient optimization. We first provide a constructive proof that self-attention mechanisms can implement reward-weighted aggregation analogous to the REINFORCE algorithm under specific weight matrix configurations, and discuss the relationship between this construction and the behavior of pretrained transformers. The correspondence is directional in hidden-state space and holds exactly only under the stated simplifying conditions; we quantify its strength empirically. Within our simplified hidden-state model, we furthermore derive an exact upper bound on the distribution shift induced by a bounded attention update, yielding a trust-region-like analogy to KL-constrained policy optimization. We validate our theory through extensive experiments across multiple LLMs, demonstrating that LLMs effectively utilize score information to shift output distributions toward high-scoring exemplars, and that attention weights exhibit a strong correlation with example scores.
Read the full abstract

Computation and Language

Interview with Kalle Lyytinen on "Implications of Theories of Language for Information Systems"

Kalle J. Lyytinen, Pierre Maier and Paul Ackah Toffey

Over fourty years after the initial publication of "Implications of Theories of Language for Information Systems" in MIS Quaterly, Lyytinen reflects about the origins of his publication and the developments in this area of research over the past decades. In the here presented interview, Lyytinen discusses the linguistic core of information systems also in light of recent trends and developments in the field, especially with regards to large language models and generative AI. Future research directions following a linguistic perspective on Information Systems (IS) research are outlined.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

Hao Jiang, Gangtao Xin, Yingdi Huang et al. (+35 more)

Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-scenario agentic scaling and present AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications. An extensible Domain x Capability x Atomic Difficulty taxonomy aligns these stages and enables fine-grained diagnosis with OmniaBench. AgentOmnia combines bidirectional environment-task synthesis with tool-dependency, program-structured, and solver-based pipelines, constructing 5,018 stateful environments with 255,375 tools and 52,361 tasks. Programs, solvers, and verifiers provide correctness signals, while supervised fine-tuning, online agentic reinforcement learning, and a rollback curriculum support post-training. Evaluation failures translate into Product Requirement Documents (PRDs) for targeted self-evolution. Starting from Qwen3-30B-A3B-Thinking-2507, AgentOmnia raises the pass rate on the OmniaBench challenging subset from 9.16% to 37.11% and the macro-average across OmniaBench, $\tau^2$-Bench, DeepPlanning, and VitaBench from 22.86% to 41.69%. Under a unified protocol,it leads the evaluated agentic post-trained baselines on OmniaBench and retains the highest four-benchmark macro-average. It also surpasses Qwen3-235B-A22B-Thinking-2507 on all four benchmarks and exceeds Qwen3.5-35B-A3B on the macro-average. Gains span three application splits, ten capability dimensions, eight atomic-difficulty factors, and 76 of 90 level-1 domains, indicating broad rather than category-specific improvement. A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings.
Read the full abstract

All authors Hao Jiang, Gangtao Xin, Yingdi Huang, Guojie Zhu, Jiangshan Zhang, Xinyuan Lin, Yunkun Xu, Chengyu Shen, Wenlong Fei, Jiawei Li, Yujie Fu, Sichen Kang, Tingyu Xie, Yedi Hu, Jingren Zhang, Hongcheng Gao, Jianshu Zeng, Chong Chen, Chang Guo, Chao Feng, Feng Wang, Fulin Lin, Jinchao Ma, Lang Mei, Li Huang, Liyan Liu, Qing He, Shuting Tao, Siyu Mo, Xiangnan Chen, Xiaohan Yu, Xiaoyang Li, Yanheng Hou, Yanyu Wu, Zhihan Yang, Wentao Zhang, Yang Gao, Zhao Cao

Computation and Language · Cross-listed from cs.IR

SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads

Congfei Zhang, Jingxiao Ma, Xiaodong Liu et al. (+14 more)

Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-generated queries excel at prospecting on a dense ANN index. Building on this, we propose SMART (SeMantic-aware Adaptive ReTrieval). To manage costs, a lightweight quality gate identifies coverage gaps in initial keyword results, adaptively routing only the ~10% of users who benefit from semantic prospecting to the LLM path. Offline evaluation demonstrates that this gated approach captures the bulk of semantic prospecting gains in Relevance Score while maintaining competitive re-targeting performance at a 90% reduction in LLM costs. Finally, in a 2-week online A/B test at Snap, SMART improved the ad conversion rate by +27.6% over a strong embedding-based baseline.
Read the full abstract

All authors Congfei Zhang, Jingxiao Ma, Xiaodong Liu, Hsiang-wei Chao, Siman Wang, Ge Liu, Shantanu Aggarwal, Vincent Zhang, Meghana Missula, Rachel Liao, Zichu Li, Xiao Bai, Yunzhi Zhou, Yajun Wang, Zhe Liu, Jinchao Li, Yu Zhang

Computation and Language

LoRA for Gender-Inclusive Rewriting and Activation Steering for Counter-Narrative Generation

Akhil Rajeev P and Manoj Balaji J

Gender-inclusive language generation seeks to transform biased text into inclusive alternatives while preserving semantic meaning and contextual coherence. This paper presents the IHLC system for the LT-EDI 2026 Shared Task, addressing both gender-inclusive rewriting and counter-narrative generation. For gender-inclusive rewriting, we employ parameter-efficient Low-Rank Adaptation (LoRA) fine-tuning, achieving an official score of 80.00%. Our primary contribution is a compute-efficient inference-time representation engineering approach for counter-narrative generation. We derive a principal steering direction from contrastive hidden-state activations using principal component analysis (PCA) and inject it into the intermediate representations of Gemma-3-4B-it during inference, enabling behavioral steering toward inclusive responses without modifying model weights. Combined with constrained prompting, this approach produces polite and contextually appropriate counter-narratives, achieving an official score of 78.12%. We further present a manual analysis of steering behavior, identifying key failure modes including semantic drift, residual bias leakage, layer sensitivity, over-steering, and text degeneration. Our findings highlight both the practical potential and current limitations of activation steering as a lightweight alternative to parameter updates for controllable and socially aligned language generation.
Read the full abstract

Computation and Language

Attention-Guided Layer Selection for Contrastive Decoding in Large Language Models

Yusuke Sakai, Natthawut Kertkeidkachorn and Kiyoaki Shirai

Contrastive decoding methods such as DoLa improve the factuality of Large Language Models (LLMs) by contrasting the output distributions of mature and premature layers. However, DoLa's dynamic layer selection relies solely on divergences in output vocabulary distributions. In this work, we propose three attention-guided strategies: Attention-JSD, Attention-Entropy-Max, and Attention-Entropy-Min, which leverage structural information carried by internal self-attention mechanisms as a signal for layer selection. Experimental results on TruthfulQA demonstrate that our strategies, particularly Attention-JSD and Attention-Entropy-Min, consistently outperform the original DoLa. We observe significant gains on multi-answer metrics (MC2 and MC3), suggesting that attention distributions can provide a more sensitive signal for resolving factual knowledge than output vocabulary distributions.
Read the full abstract

Computation and Language

ADAGE: A Language-Agnostic Pipeline for Analogical Reasoning Evaluation

Ahmed Haj Ahmed and Alvin Grissom II

Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning. We introduce ADAGE (Analogical Difficulty-by-design Assessment for Grounded Evaluation), a language-agnostic pipeline that combines native-speaker curation with LLM-assisted generation to construct challenging, translation-free benchmarks for abstract analogical reasoning. We validate ADAGE by constructing benchmarks for Arabic, Amharic, and Japanese. Evaluating 14 open-weight models, we find a consistent cultural reasoning gap: models that perform well on English proverb reasoning struggle substantially on all three native benchmarks, with accuracy dropping by 12–52 percentage points relative to English. We release the pipeline, all three benchmarks, and the full evaluation suite.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

Dhruvil S, Fenil Sojitra and Ravirajsinh Chauhan

Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference. Despite its adoption in massive production models, no prior work has studied what information this bottleneck preserves or discards, nor how it reshapes internal transformer circuits. We present the first comprehensive mechanistic interpretability study of MLA, training a 114M-parameter transformer (pretrained on a web/code/math mixture, fine-tuned on TinyStories) and analyzing its representations through SVD, attention head taxonomy, linear probing, and a disruption-attribution analysis. Our key findings are: (1) the cKV bottleneck learns a pure content representation, preserving entity identity (98% retention) while discarding positional information, validating MLA's separation of content from position via RoPE; (2) induction heads co-locate at a single layer (Layer 12), unlike their distributed formation in standard MHA; (3) a single "semantic hub" layer (Layer 15) simultaneously exhibits the highest SVD effective rank and strongest disruption-attribution score; and (4) the bottleneck is globally over-provisioned, using only 46% of its capacity on average. These findings suggest MLA does not merely compress attention passively, but reshapes how the model organizes content, position, and circuit structure. We view this as an initial data point and detail scope limitations in Section 5.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

Sultan Alshehri, Zhantao Yang, Han Zhang et al. (+1 more)

Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable. We trace this to an interface-level Bag-of-Concepts effect, where similarity scores approximate mean pooling of concept evidence regardless of operators. Although operator-dependent signals exist in text embeddings, they are too weak or misaligned to affect rankings. Fine-tuning does not reliably resolve this failure because the dominant bottleneck is how similarity aggregates evidence rather than what encoders represent. We propose factored inference, which separates evidence extraction from constraint execution, and introduce LCSE (Logic-Constrained Score Editing), a training-free method that executes constraints externally using concept scores from frozen encoders. We also introduce FACTOR-Bench, where LCSE achieves 85.5% accuracy versus 73.2% for the best fine-tuned baseline, 90.7% when applied to SigLIP 2, and improves NegBench COCO MCQ accuracy from 27.2% to 65.2% while preserving retrieval performance.
Read the full abstract

All authors Sultan Alshehri, Zhantao Yang, Han Zhang, Marios Savvides

Computation and Language

Speech Signals Complement LLMs for Predicting Interpersonal Attraction in Speed Dating

Yuriko Kikuchi, Takato Hayashi, Ryusei Kimura et al. (+3 more)

Large language models (LLMs) can predict interpersonal attraction from conversation transcripts, but it remains unclear what a speech predictor can add beyond transcript-only LLM prediction. Using Japanese speed-dating conversations, we combine predictions from a transcript-only LLM and a supervised speech predictor to estimate participants' reported liking of their partners. We show that speech can complement transcript-only LLM prediction, but that this complementarity is conditional rather than universal. Combining the two predictions significantly improves pairwise ranking accuracy over the transcript-only LLM alone in all evaluated conditions. By contrast, gains in per-participant Pearson $r$ vary across conversation rounds and rating directions, with none significant after correction. Retrospectively, these $r$ gains are concentrated among participants for whom the speech predictor is more accurate. Speech can therefore retain predictive value even when an LLM predicts attraction from transcripts. The relevant question is not simply whether speech helps, but where its complementarity emerges.
Read the full abstract

All authors Yuriko Kikuchi, Takato Hayashi, Ryusei Kimura, Naoya Inoue, Ryo Ishii, Shogo Okada

Computation and Language

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning

Xiaokun Wang, Siyu Song, Wentao Liu et al. (+1 more)

Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), and directness (R_dir), together with a K_query correction for student-introduced terms. We introduce Scaffolding Effectiveness (SE) and Conversation Depth (CD) to evaluate outcomes beyond surface fluency. On 30 held-out questions, the best GRPO variant improves SE from 30.0% to 63.3% and lowers keyword leakage from 30.0% to 13.3%. Notably, this best variant omits the directness penalty during optimization, suggesting that explicit anti-leakage terms can conflict with gradient-based behavioral alignment. An unaligned Qwen-72B baseline reaches 0% SE and 96.7% leakage, showing that scale alone does not induce Socratic behavior.
Read the full abstract

All authors Xiaokun Wang, Siyu Song, Wentao Liu, Xiaodong Zou

Computation and Language · Cross-listed from cs.AI

ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control

Yan Zhang and Shibo Li

LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning. A hallucinated fact written at one step therefore persists as a false premise for every subsequent step, a failure mode we call memory contamination. Existing memory management addresses retrieval and capacity but not write-time correctness; this admission problem cannot be solved by utility- or recency-based criteria, and uncontrolled contamination compounds across long trajectories. We propose ConsistencyGate, a write-time admission gate that, before committing a candidate fact m extracted from context c, queries the LLM K times for a soft support score and admits m only when the average exceeds a threshold. The mechanism is model-agnostic, requires no fine-tuning, and reduces to a single forward pass in a log-probability variant for latency-sensitive deployments. To measure the effect on natural data, we construct two real-conversation benchmarks (LoCoMo-Contam and MSC-Contam) by planting controlled single-detail corruptions in long-term conversations from LoCoMo and MSC, and complement them with a structured synthetic corpus (MemContam) that isolates a near-oracle upper bound. Across four LLM backbones, ConsistencyGate reduces contamination on every benchmark relative to a write-everything baseline, with the cost concentrated on facts that are stated only implicitly in the source context. We release all three benchmarks together with the gate implementation.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses

Yan Zhang, Shikan Lian and Shibo Li

Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta). The framework is interpretable, but it commits to a single hypothesis with no measure of uncertainty, and that hypothesis varies substantially across optimization runs on the same data. We propose the Verbalized Particle Posterior (VPP), which treats verbalized learning as a Bayesian inference problem: maintain a population of natural-language hypotheses as particles, update them with Metropolis-Hastings (VPP-MH) or Sequential Monte Carlo (VPP-SMC), and predict by Bayesian model averaging. Both algorithms treat the LLM as a black box, requiring no access to logits or gradients. A distinctive consequence follows. In classical Bayesian learning, model selection sits outside the posterior; in VPP both model structure and parameters share a single language space, and the posterior ranges over both. We evaluate VPP on regression, classification, and rule-discovery benchmarks. It improves over a single VML run on every benchmark and matches or exceeds an oracle-best ensemble of independent VML runs on most, while eliminating the catastrophic single-run failures that VML occasionally produces. Because each particle is a human-readable hypothesis, the posterior is itself something a reader can inspect, seeing in plain text which explanations the data supported and which it ruled out.
Read the full abstract

Friday 24 July

Computation and Language

Memory That Looks Forward: A Zero-Inference Prospective Term for Personal Memory Retrieval

Jonathan Groff

Retrieval over a personal memory store is retrospective: it surfaces what resembles the query, and it is blind to what the user has committed to do. We describe a prospective term for memory retrieval that costs no inference at query time. Commitments are held in an explicit ledger as dated or trigger-conditioned entries; memory items linked to a firing entry receive a salience boost, blended multiplicatively into embedding-based retrieval so that relevance remains sovereign. On a synthetic prospective-memory task set modeled on TriggerBench's published structure (48 blind-authored dialogues, 175 tasks), the term raised recall@5 on the hard stratum from 0.000 to 0.955 at the default blend weight and to 1.000 under a floor variant, with zero false boosts across 53 resolved-commitment tasks. Blind authorship also produced a scope finding: only 17-29% of naturally phrased commitment-trigger pairs defeat embedding similarity, so the term matters on a real minority of cases and must do no harm on the rest, which it does not. We position precomputed commitment linkage as the always-on floor of a layered design whose expansion layer is query-time prospection. Results are preliminary: the evaluation set is author-constructed, and evaluation on TriggerBench proper is committed follow-up work once its data is released.
Read the full abstract

Computation and Language

Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge

Zhecheng Ren, Xuanji He, Xiaoxiao Li et al. (+5 more)

This paper presents the Transsion Speech Team submission to Task 1 of the MLC-SLM 2026 Challenge, which focuses on speaker-attributed transcription for multilingual conversational speech. We propose a cascaded framework consisting of three components: a speaker diarization module, a long-form multilingual ASR module, and a speaker-transcription fusion module. The diarization module is built upon DiariZen and produces speaker-homogeneous segments through local speaker activity estimation and global speaker clustering. The ASR module is based on Qwen3-Omni and generates multilingual transcriptions, while an external CTC-based alignment model provides precise word- and character-level timestamps. Finally, the fusion module combines diarization outputs with timestamped transcriptions to generate speaker-attributed STM outputs. Experimental results on the official evaluation set demonstrate the effectiveness of the proposed framework. The submitted system achieves a tcpMER of 15.41% and ranks second among all participating teams.
Read the full abstract

All authors Zhecheng Ren, Xuanji He, Xiaoxiao Li, Zhichen Han, Gaoyang Dong, Gaosheng Zhang, Minchuan Chen, Fengjie Zhu

Computation and Language

Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes

Qirui Chen, Renjie Pi, Jiahui Gao et al. (+1 more)

Data-driven fine-tuning is widely adopted to enhance reasoning in Large Language Models (LLMs) due to its simplicity and efficiency. However, mainstream imitation learning methods that rely exclusively on perfect reasoning trajectories suffer from a Scaling Collapse: when the problem set is limited, increasing positive examples fails to yield continuous improvement. However, during inference, an LLM can not guarantee that every intermediate step is correct and is therefore prone to errors. Once such errors arise, the LLM often struggles to recover and may be further misled by the accumulation of previous mistakes. To address this, we propose Reflective Recovery, a simple yet effective self-supervised approach that transforms failed reasoning attempts into recovery training data. Specifically, we extract initial segments of failed trajectories, concatenate them with prompts, and use them to guide the LLM toward valid solutions. Because these segments from failed trajectories are likely to contain errors, this process teaches models to recognize and correct mistakes during reasoning, enabling recovery from erroneous states without relying on external critics or reward models. Evaluated on extensive benchmarks, Reflective Recovery significantly improves performance. On DeepSeek-R1-Distill-Qwen-7B, it boosts accuracy from 30.0% to 37.5% on AIME 2025 and from 37.6% to 47.8% on Minerva. More importantly, analyses demonstrate that it breaks the scaling collapse barrier and enables models to develop emergent self-correction behaviors, representing a paradigm shift from outcome-oriented memorization to process-oriented reflective reasoning.
Read the full abstract

All authors Qirui Chen, Renjie Pi, Jiahui Gao, Lingpeng Kong

Computation and Language

DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models

Xin Zhang, Yili Wang, Yue Tan et al. (+6 more)

Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation. However, similar to autoregressive LLMs, D-LLMs remain vulnerable to hallucinations, where fluent outputs may contain factually incorrect or unsupported content. Although existing hallucination detection methods for D-LLMs attempt to leverage uncertainty trajectories of the denoising process to better identify hallucination signals, they typically compress the trajectories along either the temporal or token dimension, overlooking the useful information encoded in the complete two-dimensional token-step structure. Consequently, they may fail to capture hallucination-relevant patterns, such as inconsistent convergence and cross-token fault propagation, leading to suboptimal detection performance. To bridge this gap, we propose a D-LLM hallucination detection framework that formulates the Denoising trajectories as Multivariate Time Series over learnable latent variables (DeMTS for short). DeMTS employs a trajectory-preserving token-to-variable assignment module to convert token signals into stable latent variables. Based on these variables, we propose dynamic multivariate temporal modeling to progressively integrate inter-variable dependency modeling with temporal encoding for hallucination prediction. Extensive experiments on two D-LLMs backbones and three benchmarks demonstrate that DeMTS outperforms existing hallucination detection methods while maintaining strong robustness, efficiency, and cross-task transferability.
Read the full abstract

All authors Xin Zhang, Yili Wang, Yue Tan, Xin He, Yanyu Qian, Yixin Liu, Yi Chang, Shirui Pan, Xin Wang

Computation and Language

Characterizing Rhetorical Misalignment in Decision-Making with Language Models

Zirui Cheng, Joey Chan, Simo Du et al. (+3 more)

Human decision-making is often shaped by a range of well-documented cognitive biases. As large language models (LLMs) become increasingly integrated into high-stakes human-AI decision-making, it is important to understand whether their outputs can amplify potential biases, how this influences human decisions, and crucially, whether it can lead to harmful consequences. In this work, we develop a decision-theoretic framework to study rhetorical misalignment, a failure mode where an LLM uses rhetorically inappropriate forms of presentation for a given decision context, thereby inducing suboptimal human decisions. We empirically investigate this phenomenon through a human-subject experiment in realistic clinical decision-making using a dataset curated from the United States Medical Licensing Examination. By measuring how LLM-generated information affects decisions, we observe that LLMs induce an average 2.81% rate of harmful decision flips across different models, where clinician participants change from a correct to an incorrect answer. Rationales reported by participants provide evidence that these revisions are closely related to the language used by LLMs that may induce different types of cognitive biases, including anchoring, authority bias, and loss aversion. To enable scalable evaluation, we instantiate our theoretical framework using decision-makers simulated by LLMs to computationally measure rhetorical misalignment. Our findings reveal a safety concern previously unrecognized in high-stakes domains: a model can be factually aligned yet still induce harm through its rhetorical presentation.
Read the full abstract

All authors Zirui Cheng, Joey Chan, Simo Du, Chenhao Tan, Yue Guo, Hao Peng

Computation and Language

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

Tejaswi V. Panchagnula, Bruce Coburn, Bryce J. Dietrich et al. (+3 more)

As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI). Current model alignment paradigms, such as reinforcement learning from human feedback (RLHF), make LLMs follow overarching safety instructions. However, this instruction tuning can be exploited via adversarial prompt injection and be used to generate unsafe content. In particular, political bias has not been specifically targeted by modern alignment techniques as harmful and biased content. To address this vulnerability of LLMs, we propose mitigation strategies using Chain of Thought (CoT) prompting and Direct Preference Optimization (DPO). Using a public dataset of legislative videos, we generate summaries using LLMs, inject bias via adversarial prompting and evaluate their performance on a four axis scale designed for political summarization. In this paper, we present different methods to shield LLMs against the injection of political bias. Our results demonstrate that the proposed Recursive Self-Correction approach raises model performance from a Political Neutrality Likert scale baseline of 2.14 to 4.56, averaged across all models, demonstrating effective inference-time mitigation of political bias in LLM-generated summaries.
Read the full abstract

All authors Tejaswi V. Panchagnula, Bruce Coburn, Bryce J. Dietrich, Robert X. Browning, Edward J. Delp, Fengqing Zhu

Computation and Language

Search-G1: Co-Evolving Representation-Based Rewards for Selective Grounded Search

Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang et al. (+7 more)

Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Yet terminal correctness assigns equal credit to direct answers from parametric knowledge, evidence-grounded answers, and answers recalled after redundant search. Process supervision and LLM judges provide richer feedback but can require high-cost annotation or inference; low-cost, non-contrastive policy confidence signals do not directly identify whether retrieved evidence changes an answer. We propose Search-G1, a reward framework that couples retrieval necessity with evidence reliance through two intervention-calibrated hidden-state readouts for selective grounded search. A prompt readout predicts closed-book sufficiency, whose complement proxies policy-relative retrieval necessity; an answer-commit readout predicts evidence reliance as sensitivity to evidence deletion conditional on the realized reasoning prefix. A correctness-first reward gates evidence-reliance credit by retrieval necessity, rewards sufficient direct answers, and penalizes repeated search. After calibration, scoring needs neither process annotations nor LLM-judge inference. As policy-relative targets, trajectory distributions, and representations may drift, Search-G1 periodically regenerates targets and refits its readouts. Across four QA benchmarks and two scales, Search-G1 achieves competitive task accuracy, with stronger counterfactual evidence dependence and fewer searches in the main comparisons, complemented by independent human audits of answer support.
Read the full abstract

All authors Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang, Junming Zhang, Ranjie Duan, Qiaolin Xia, Hao Wang, Yu Lu, Haibo Shi, Xingjun Ma

Computation and Language · Cross-listed from cs.AI

NL2SHACL-Bench: A Benchmark Suite for Natural Language to SHACL Translation

Yuchen Zhou, Niels Bobet and Maribel Acosta

SHACL is a core technology for validating the conformance of RDF knowledge graphs (KGs). Yet, authoring SHACL shapes requires technical expertise that most domain experts lack. Translating natural language requirements into SHACL (NL2SHACL) would lower this barrier. However, there is no dedicated benchmark for NL2SHACL, and evaluating generated shapes requires methods beyond string comparison, as semantically equivalent shapes can differ in serialisation and structure. To tackle these challenges, we present NL2SHACL-Bench, a benchmark suite for natural language to SHACL translation. Using NL2SHACL-Bench, we evaluate four state-of-the-art large language models (LLMs) for this task. Our results show that current LLMs are highly capable of generating syntactically valid SHACL, but still struggle to produce semantically equivalent constraints for complex logical and structural patterns. This indicates that NL2SHACL-Bench provides a meaningful basis for measuring advances in the NL2SHACL state of the art.
Read the full abstract

Computation and Language

WuYuEval: A Multi-Level Benchmark for Large Language Models in Solid Waste Management

Yi Zhang, Hongyang Wang, Zheng Hao Leong et al. (+11 more)

Large language models (LLMs) are increasingly used as technical assistants, but their competence in solid waste management (SWM) remains difficult to assess because existing benchmarks emphasize general knowledge rather than professional decisions under engineering, environmental, and policy constraints. We introduce WuYuEval, a multi-level benchmark for evaluating LLMs in SWM across foundational knowledge, domain reasoning, and expert decision-making. After quality auditing, WuYuEval contains a Foundation Module with 4,590 closed-ended multiple-choice questions across six task types and eight domain categories, together with an Expert Module with 247 scenario-based open-ended questions involving multi-objective optimization, constraint trade-offs, and system design. For expert tasks, we combine anchor-calibrated LLM-as-a-Judge scoring with Elo-based pairwise comparison. Across 33 LLMs, performance varied widely. The leading model reached 94.64% accuracy on the Foundation Module, but average accuracy still fell from 84.14% on easy questions to 42.50% on hard questions, with lower performance concentrated in calculation, experimental design, urban planning, and open-ended expert tasks. Reasoning-oriented Thinking modes improve most matched model pairs after auditing, but the gains depend on baseline capability and are not uniformly positive. These results suggest that visible deliberation helps only when it remains anchored to units, assumptions, and engineering constraints; otherwise, it may drift from decisive answer boundaries. WuYuEval therefore provides both an evaluation resource and an empirical basis for developing SWM-oriented foundation models with professional reasoning chains and explicit constraint control.
Read the full abstract

All authors Yi Zhang, Hongyang Wang, Zheng Hao Leong, Zihao Wu, Kaijun Lin, Zhixing Pan, Qixun Huangfu, Wei Ren, Wenyan Wu, Fangyun Wang, Wenting Yu, Hengyu Lin, Muling Yang, Zongguo Wen

Computation and Language

Predicting Startup Exit from Textual Descriptors - A Computational Linguistics Framework

Alberto M.G. Saruggia and Sebastien Germano

This study shows that textual descriptors alone can predict early-stage startup success, defined as Exit, without relying on contextual, financial, or human capital variables. Using venture capital-curated datasets covering 7,419 startups over 20 years, the research isolates text-based framing variables and engineers 850 features via startup narrative mapping. Data subsets and vector embeddings are evaluated for statistical significance, followed by supervised machine learning experiments across six models. Binary Exit prediction using Logistic Regression attains an F1 of 0.48 with 0.55 recall using all features (excluding embeddings), and an F1 of 0.26 with 0.59 recall using textual descriptors only (including embeddings). Feature analysis indicates that optimized densities of hyping markers such as adjectives, jargon, and buzzwords are associated with higher Exit probability, while excessive statement or name length is associated with lower probability. The study also introduces a quantifiable Hyping Score for potential application in venture screening. Findings indicate that startup framing can serve as standalone predictor of economic outcomes, in high-information-asymmetry investment environments.
Read the full abstract

Computation and Language · Cross-listed from cs.IR

Two Views, One Voice: Evidence-Grounded Conversational Music Recommendation

Sungwook Yoo and Sewook Yoo

Traditional conversational recommenders entangle retrieval and response generation within a single text interface, so exact entity cues fade as the dialogue's intent evolves, which compromises explanation credibility. We address this within the ACM RecSys Challenge 2026, which mandates both top-20 ranking and evidence-grounded response generation. This paper presents the third-place solution by team "swyoo" for the Blind-B industry track. We decouple retrieval and response into separate pipelines connected strictly via ranked tracks and metadata. Retrieval combines a hybrid lexical-dense pool for exact matching with a task-adapted pool driven by fine-tuned Qwen 8B adapters. Candidates are calibrated via LightGBM, then routed to an evidence-grounded propose-assign-select (PAS) framework to structure responses. This system also ranked second on the explanation-quality leaderboard in the final blind evaluation. Our findings demonstrate that: (i) isolating retrieval and response preserves both catalog cues and fluid intent; (ii) structuring generation via explicit evidence assignment is key to this near-best-in-class explanation reliability.
Read the full abstract

Computation and Language

Neuromorphic Diffusion Language Models: Addressing Compute and Memory Bottlenecks via Sparsity and Block Denoising

Dengyu Wu, Clement Ruah, Jiechen Chen et al. (+2 more)

Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full set of model parameters, leading to low operational intensity and high energy consumption. Masked diffusion language models (MDLMs) partially address this limitation for memory-bound settings by allowing multiple tokens to be generated per parameter access. In order to further enhance inference efficiency on modern platforms with extensive in-chip memory, this work proposes neuromorphic MDLMs (N-MDLMs), which integrate block diffusion with spike-based neuromorphic computation to jointly improve throughput and energy efficiency. While block diffusion increases token throughput by producing multiple tokens per parameter access, spike-induced sparsity reduces effective parameter traffic and computations by skipping inactive channels. To analyze the synergistic effect of sparsity and diffusion, we develop a token-level roofline-inspired model that captures the combined impact of block-parallel generation and spike sparsity on decoding efficiency. Experimental results on translation tasks show that, thanks to spike-induced sparsity, N-MDLMs achieve substantial improvements in energy efficiency and throughput even in compute-bound platforms for which MDLMs would fail to improve over AR-LLMs.
Read the full abstract

All authors Dengyu Wu, Clement Ruah, Jiechen Chen, Bipin Rajendran, Osvaldo Simeone