Searcharxiv⌕ Search

subject

cs.CL

cs.CL: explore 1934 source-linked works published from 2017 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Search within this collection

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated perspective. Humans infer such perspectives from shared environmental knowledge, activity context, and commonsense. Recent vision-language models (VLMs) appear capable of spatial reasoning, but their ability to infer a speaker's viewpoint from contextual cues and interpret situated spatial relations from that viewpoint remains unclear. We call this capability contextual observer grounding. To study this capability, we construct the Point-of-View Benchmark (POVBench), a dataset of 3D scenes and queries that disentangles Inferred, Stated, and Given forms of observer grounding in natural embodied communication. Given multi-view observations and a natural-language sentence, models must localize unseen or underspecified targets from situated spatial and contextual cues. Across state-of-the-art VLMs, localizing targets from directional language remains challenging, even when observer grounding is made explicit. We find that explicit breakdowns of observer-relative spatial reasoning improve target localization. Our project page is available at https://mimo-owl.github.io/POVBench/.

cs.CV↗
arXiv2026

Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation

Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational efficiency, and implicit modeling of human preferences. Interestingly, iterative extensions of DPO have achieved stronger performance on academic benchmarks, raising two key questions: (i) Why do iterative methods generally outperform offline ones? (ii) Can their advantages be incorporated into offline alignment? To answer the first question, our controlled experiments reveal that the explicit preference model, additionally introduced in the iterative procedure, is a key factor behind its superiority over offline methods. This insight leads us to answer the second question affirmatively and propose Distilled Preference Probability Policy Optimization (DP3O), an effective and efficient offline alignment algorithm. DP3O first learns an explicit preference model using a helper class of LLMs and then distills its knowledge into policy optimization. Theoretically, we show that explicit preference modeling admits better estimation error control than implicit formulations, and that DP3O achieves a tighter generalization bound than hard-label DPO through variance reduction. Empirically, we evaluate DP3O on a wide range of chat-based and downstream tasks and show that it outperforms state-of-the-art offline methods, achieves performance comparable to iterative DPO, and reduces training time by about $42\%$, demonstrating both its effectiveness and efficiency.

cs.CL↗
arXiv2026

Dynamic-Programming-Guided Hierarchical BPE and Empirical Analysis of Vocabulary Pruning

Byte Pair Encoding (BPE) constructs vocabularies through greedy pair merging, but the resulting merge order does not necessarily allocate a fixed model-visible vocabulary optimally for compression. We propose Dynamic-Programming-Guided Hierarchical BPE (DH-BPE), a vocabulary-construction method that combines token exposure under exact minimum-token segmentation with the hierarchical dependencies induced by BPE training. Starting from a modestly overshot BPE candidate vocabulary, DH-BPE uses dynamic programming to measure candidate utility and applies exposure-guided, dependency-aware pruning to select a fixed-size model-visible vocabulary. We compare DH-BPE against Standard BPE and recent vocabulary-optimization baselines, including Pruned BPE, MinGram, and MinGram-PP, in primary evaluations at 12K and 16K target vocabulary sizes, with an additional 18K evaluation against MinGram only. Across the primary 12K and 16K comparisons, DH-BPE consistently improves aggregate compression over Standard BPE, Pruned BPE, and MinGram under a shared exact minimum-token DP encoder. MinGram-PP achieves stronger aggregate compression in the primary comparisons, but DH-BPE outperforms it at overshoot factors f = 2.0 and f = 3.0 in cross-corpus evaluation; at 12K, MinGram-PP reverses this ordering only with the substantially larger candidate pools at f = 4.0 and f = 5.0. Qualitative analysis further shows that DH-BPE balances later, more complete BPE merges with reusable subword components, providing a practical approach to improving vocabulary allocation under a fixed model-visible vocabulary budget.

cs.CL↗
arXiv2026

TurEngMix: A Text Corpus and Benchmark for Turkish-English Code-Mixed Language Identification and Named Entity Recognition

Natural language processing systems underperform on code-mixed text, particularly for low-resource language pairs. Turkish-English poses a further challenge: it lets English stems combine with Turkish suffixes to form single mixed-language tokens. We introduce TurEngMix, a corpus of 5.5K noisy, naturally occurring social media posts (486,974 tokens) rich in Turkish-English code-mixing. From this corpus, we construct a new Turkish-English benchmark for code-mixed language identification (LID) and named entity recognition (NER), comprising 15K expert-annotated tokens. Evaluating both decoder LLM and fine-tuned encoder baselines, we find that monolingual Turkish and English tokens are labeled reliably, but all models have high error rates on mixed-language tokens for both LID and NER. For morphologically integrated tokens, NER error rates were 5.2x and 6.3x higher for GPT-4o and Qwen, respectively. This highlights how morphological integration remains a challenge. We release the corpus, annotations, and code to support future computational and sociolinguistic research on Turkish-English code-mixing.

cs.CL↗
arXiv2026

MOLE: Detecting Insider Threats in AI Agents

Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison training data, or weaken release gates. Existing benchmarks do not test whether defenders can detect this activity among routine work under a limited review budget. We introduce MOLE, an open benchmark of 150 AI-operated accounts sharing 9 stateful services over 30 workdays, with 12 threats and 8 corpora from four models totaling roughly 20 billion tokens. Of 39 agent models, 72% complete most assigned harmful objectives and agent refusal does not predict completion. MOLE enables comparison of 40 monitors across corpus generators, observability levels, and threats; even the best evaluated monitor in our single-day audit-event comparison misses nearly half of completed harm. MOLE also enables monitor development: benchmark-guided search improves a mid-tier monitor by 49-64%, while selective use of a stronger monitor improves budget-AUC by 10% over applying it to every account-day at comparable modeled cost.

cs.LG↗
arXiv2026

CantoneseLLM v2: Reasoning in a Low-Resource Language

Cantonese is widely spoken but remains low-resource in written data, with no large corpus of native Cantonese reasoning traces available for model training. We develop and release CantoneseLLM v2, comprising models based on Qwen3 8B and 30B-A3B. The models are trained through CPT on 784 million Cantonese and Hong Kong-related tokens, chat-vector merging, SFT, DPO, and RLVR. Evaluation across the training stages shows that chat-vector merging transfers instruction following but preserves the donor model's reasoning language, while SFT with limited Cantonese reasoning data substantially shortens or removes reasoning traces and reduces benchmark performance. DPO restores the reasoning-block format, particularly for the 8B model, but recovers only part of the lost performance. The RLVR training with Cantonese language and Traditional Chinese scripts as multiplicative constraints introduced Cantonese language alignment and restored the lost performance. The 30B-A3B model reaches 73.16 on HKCanto-Eval, within 1.20 points of its merged checkpoint, while retaining the Cantonese reasoning behaviour absent from that checkpoint. We release the model checkpoints, the training environments, and a thirteen-year Traditional Chinese Common Crawl dataset. The models can be accessed at https://huggingface.co/collections/hon9kon9ize/cantonesellm-v20

cs.CL↗
arXiv2026

Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning

Large language models achieve strong performance across diverse tasks, but deployment remains costly because of memory, latency, and energy demands. Structured pruning reduces these costs by removing architectural components, yet its recovery stage is often limited by a mismatch between the recovery module's representational capacity and the complexity of the removed knowledge. We call this bottleneck the capacity-knowledge asymmetry and propose OverRep, an Overcomplete Reparameterization framework for structured LLM pruning. Following the principle of "train overcomplete, deploy compact", OverRep temporarily overparameterizes the recovery module during training to absorb complex knowledge distilled from the original model. After recovery, the overcomplete re-parameterization is algebraically merged into a mathematically equivalent compact module, preserving the pruned model's inference-time architecture and computational cost. OverRep further introduces an annealed activation that enables nonlinear training dynamics while converging to a linear regime for exact algebraic merging. Across three backbone families, OverRep improves retained reasoning performance over strong recovery baselines by up to 5.5 and 8.4 points at 25% and 50% pruning, respectively, while keeping memory usage and TFLOPs comparable to existing recovery methods. Our code is available at https://github.com/mmai-laboratory/OverRep.

cs.CL↗
arXiv2026

Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning

We identify the Flow Moment, a reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the revision- and backtracking-oriented Aha Moment. We refer to their corresponding linguistic expressions as Flow Markers and Aha Markers, respectively. Based on this observation, we construct Flow-CoT by rewriting the discourse markers of original reasoning traces while preserving their underlying reasoning content, and use it as auxiliary supervision for on-policy self-distillation (OPSD). We further propose \textbf{Aha-Flow Distillation (AFD)}, a dual-mode extension of OPSD that pairs different forms of privileged information with corresponding reasoning instructions. The Aha branch retains concise solution-based supervision, while the Flow branch introduces rewritten Flow-CoT under a direct and confident reasoning instruction. At inference time, the model uses only the standard reflective instruction, so Flow-style reasoning serves purely as a training signal. Experiments on AIME25 and HMMT25 show consistent improvements across Qwen3-8B and Qwen3-4B: AFD improves Avg@12 from 60.8 to 61.3 on Qwen3-8B and from 57.5 to 58.6 on Qwen3-4B over our reproduced OPSD baselines. Controlled ablations further show that, with the same Flow-CoT/Aha-CoT composition, dual-mode training improves Avg@12 from 59.5 to 60.1, indicating that the benefit comes not only from introducing heterogeneous reasoning supervision, but also from how it is organized during self-distillation. The code is available at https://github.com/Wang-Xiaodong1899/Aha-Flow-Distillation.

cs.CL↗
arXiv2026

A Hyperbolicity Atlas of Large Language Model Hidden States

LLM hidden states are ordinary vectors, but the distances among those vectors may still show hierarchical structure. To our knowledge, this paper is the first systematic study of whether prompt-token hidden states in contemporary LLMs exhibit Gromov Hyperbolicity (GH), a distance-based measure of tree-likeness. Using 818,904 sample-layer measurements from ten open-weight models across MATH500, HumanEval, WinoGrande, and TruthfulQA, we build a GH map over four axes: parameter scale, layer depth, model family, and input domain. The clearest pattern is depth, not scale: middle layers usually form a high-relative-hyperbolicity plateau, while final layers often become substantially more tree-like. Scale effects are weak and non-monotonic, matched 7/8B model families differ strongly, and domains interact with model specialization. These findings make GH useful as a practical diagnostic: it shows where hierarchical distance structure appears, how specialization changes it, and which model-layer-domain comparisons deserve closer analysis.

cs.CL↗
arXiv2026

Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection

Voice phishing detection faces three critical challenges: real criminal recordings are unavailable due to privacy constraints; when available, only a handful of samples exist, insufficient for fine-tuning; and lightweight acoustic-only detection is needed as an alternative to large self-supervised models. We compare domain-invariant prosodic features and self-supervised representations (HuBERT, wav2vec2.0) through cross-domain evaluation-training on scenario-based actor recordings and testing on authentic criminal calls. Domain-invariant prosodic features achieve 69.5% F1 zero-shot and 71.0% with 5-shot learning. HuBERT achieves highest performance (94.2% F1, 5-shot), while wav2vec2.0 exhibits a precision-oriented detection profile (90.2% F1 with 99.4% precision, 5-shot). These findings reveal fundamental trade-offs: domain-invariant features enable zero-shot deployment when no real data exists, while SSL methods achieve higher performance but require real samples and compute.

cs.SD↗
arXiv2026

Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets

LLM assistants often produce more answers than humans can review before users see them. Most evaluations ask whether an answer is wrong, unsupported, or low-confidence. Bounded review budgets instead ask which answers should be checked first under a fixed review budget. Risk alone is not enough: a high-risk answer may be hard to repair, while a moderately risky answer may be directly correctable from available evidence. For generated-answer evaluation, we model review prioritization as exposure reduction, where review value combines estimated wrongness, intervention affordance, impact, and cost. We evaluate review queues with Wrong-Answer Exposure Ratio (WAER), the fraction of wrong answers left unreviewed, and post-repair residual exposure (PRRE), the fraction still exposed after deterministic benchmark-supported repairs. PRRE uses repairability rules that do not numerically reuse the affordance scores used for ranking. On a 720-item TAT-QA/SciFact stress benchmark, review-value ranking keeps answer-level WAER nearly unchanged at 20% budget (0.605 vs. 0.600) but lowers PRRE from 0.881 to 0.716. These results show that trustworthy LLM evaluation should measure not only error detection, but also how limited review capacity reduces exposed wrong answers.

cs.AI↗
arXiv2026

Revisiting Complete Reasoning Traces for Post-Training

Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning capability. Such trajectories tend to be long due to complex, interwoven paths, which often include detours on the path toward the answer. However, it has been underexplored whether LLMs indeed benefit from learning complete trajectories in post-training, such as supervised fine-tuning (SFT). Starting from our pilot study, we find that full trajectories provide only limited benefit, while partial trajectories are effective even under heavy truncation. We analyze redundancy in reasoning trajectories through attention-based analyses and controlled token-removal studies, both of which show that intermediate tokens contribute minimally to final reasoning quality. This suggests that avoiding redundant information may allow LLMs to internally infer coherent alternatives by inferring missing steps from their internal knowledge, given known trajectory endpoints. Furthermore, we show that training LLMs using endpoints leads to consistent changes in reasoning behavior, and that it also benefits post-training methods based on reinforcement learning or on-policy distillation, highlighting the need to revisit complete reasoning traces. Code is available at https://github.com/naver-ai/revisiting-trace.

cs.CL↗
arXiv2026

The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs

Prompt-based interventions: system prompts, personas, role instructions, reliably reshape what a language model says, but it is unclear which layer they reach. Do they reconfigure internal structure, or only modulate the output channel? We use persona conditioning as a controlled probe, measuring its effects along a depth axis from self-report, through open-ended generation, to word-level parametric association, across three instruction-tuned models. We find a graded dissociation. Personas are legible but not structural: models follow single-trait instructions yet fail to reproduce human inter-trait covariance. The dissociation deepens with depth: personas hold or amplify closed-form QA bias, shift absolute tone while leaving between-group disparity unchanged, and barely perturb an already saturated associative baseline. Prompt-based steering thus operates in the output channel and has a structural reach limit that surface manipulability can mask.

cs.CL↗
arXiv2026

PTCG: Persona-guided Tree-based Counterargument Generation

The ability to generate counterarguments is important for critical thinking and balanced discourse, yet existing approaches typically produce only a single counterargument, failing to capture the diversity and persuasiveness required in real-world debates. To address this limitation, we propose Persona-guided Tree-based Counterargument Generation (PTCG), a framework that combines Tree-of-Thoughts-inspired step-wise generation and pruning with speaker persona selection. By estimating the author's persona from the original argument and incorporating speaker personas representing distinct perspectives, PTCG operationalizes perspective-taking and enables the generation of diverse counterarguments. Results from LLM-as-a-Judge, classifier-based assessment, and human evaluations indicate that PTCG shows consistent improvements in both the diversity and persuasiveness of counterarguments compared to baseline methods.

cs.CL↗
arXiv2026

Line-Coupled Language Model

Autoregressive language models generate one token per decoding step, limiting the useful output of each forward pass. Although diffusion models, insertion-based decoding, and multi-token prediction enable parallel generation, they either incur additional training-time token traffic or struggle to predict strongly dependent future tokens. We introduce the Line-Coupled Language Model (LCLM), an autoregressive model that advances multiple text lines together by predicting the next token for every active line while coupling the lines through shared causal context. LCLM interleaves line tokens into a single causal sequence and uses line-staggered rotary positions, retaining the standard next-token objective and causal attention. Controlled experiments show that cross-line targets are substantially less dependent than consecutive same-line targets, supporting lines as parallel generation units. With 881M parameters, LCLM produces an average of 2.94 content tokens per forward pass with a validation cross-entropy loss of 2.44, compared with 1.00 token per forward pass and a loss of 2.39 for the vanilla autoregressive baseline. Most notably, even when LCLM generates 16 tokens per forward pass, its loss is only 0.09 higher than that of the vanilla autoregressive baseline (2.34 vs. 2.25).

cs.CL↗
arXiv2026

Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction

This paper presents our system for CCL2026-Eval Task 5: Minor-Grain Breeding Information Extraction (MGBIE), which jointly extracts 12 entity types and 6 relation types from minor-grain breeding literature. We propose RAME (Retrieval-Augmented Multi-Prompt Ensemble), a training-free framework that elicits multiple LLM outputs under controlled diversity and aggregates them by majority voting to obtain high-confidence predictions. RAME combines (i) retrieval-augmented few-shot selection via a hybrid BM25-embedding retriever, (ii) a three-prompt ensemble (Strict, Relaxed, Balanced) spanning the precision to recall spectrum, and (iii) large-scale repeated sampling with majority voting to filter noisy predictions. Built on DeepSeek-V4-Flash, RAME achieves a Total Score of 0.499 (NER 0.730, RE 0.346) on the leaderboard, ranking 1st and surpassing the official Track-A baseline powered by GPT-5.5 (0.448), representing an 11.4% relative improvement. Code is available at https://github.com/king-wang123/CCL26-RAME.

cs.CL↗
arXiv2026

Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise

A transformer can make an attribute linearly decodable in its residual stream at a depth where that attribute does not yet influence the output. This gap between where information is readable and where it is used has been shown for attributes stated directly in the input. We ask whether it also holds for an attribute the model must infer gradually over a conversation, namely how expert its dialogue partner is. Using ExpertCollab, a corpus of multi-turn research-planning dialogues between model-played personas at four expertise levels, we find that partner expertise is most decodable in the early layers and falls to near chance before the midpoint of the network. Counterfactual patching shows that injecting the expertise difference at the layer of peak decodability barely changes a fixed late-layer readout, whereas the same difference injected past the midpoint propagates almost completely, a separation of more than an order of magnitude. A content-matched random control and a probe-free diagnostic place the transition at the same early layer, and a statically specified control attribute stays decodable throughout. An inferred relational attribute is therefore represented well before it becomes causally active, which bounds where any attempt to read out or steer partner-conditioned behavior must intervene. We use one model on a synthetic corpus as an initial demonstration.

cs.AI↗
arXiv2026

Vishing-Tactics-Bench: Forecasting Exploitation Trajectories in Voice Phishing Calls

Voice phishing (vishing) unfolds in real time; by the time a call has ended and post-hoc classification is possible, the harm has already been done. The more actionable question is which concrete harm (Information Gathering or Financial Exploitation) an ongoing call is tactically progressing toward. We present Vishing-Tactics-Bench, a benchmark grounded in Endsley's situation-awareness (SA) framework that recasts vishing defense from after-the-fact fraud classification to harm projection: predicting at each turn whether the call will reach either terminal harm. We adapt MITRE ATT&CK to vishing as a 6-tactic taxonomy (Vishing-Tactics) and label 35,340 scammer utterances across 5,645 synthetic Chinese calls. We define Exploitation Trajectory Forecasting, a survival-style protocol over the two terminal harms with three metrics: AP@k, C-index, and divergence error. Baselines ranging from a Markov heuristic to fine-tuned LLMs show that the tactical trajectory serves as an interpretable representation of the call's tactical state, supporting harm-specific forecasting, which can then be used for the downstream application of intervention selection; a stratified lead-time analysis at a tight false-alarm budget further identifies at what point in a call the trajectory signal yields early warning.

cs.CL↗
Compare source metadata on this page
WorkPublishedSource identifierSource
Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models2026-09-072609.06880arxiv
Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation2026-09-072609.06893arxiv
Dynamic-Programming-Guided Hierarchical BPE and Empirical Analysis of Vocabulary Pruning2026-09-072609.06898arxiv
TurEngMix: A Text Corpus and Benchmark for Turkish-English Code-Mixed Language Identification and Named Entity Recognition2026-09-072609.06963arxiv
MOLE: Detecting Insider Threats in AI Agents2026-09-072609.06966arxiv
CantoneseLLM v2: Reasoning in a Low-Resource Language2026-09-072609.06970arxiv
Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning2026-09-072609.06974arxiv
Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning2026-09-072609.07036arxiv
A Hyperbolicity Atlas of Large Language Model Hidden States2026-09-072609.07053arxiv
Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection2026-09-072609.07079arxiv
Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets2026-09-072609.07095arxiv
Revisiting Complete Reasoning Traces for Post-Training2026-09-072609.07103arxiv
The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs2026-09-072609.07117arxiv
PTCG: Persona-guided Tree-based Counterargument Generation2026-09-072609.07120arxiv
Line-Coupled Language Model2026-09-072609.07129arxiv
Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction2026-09-072609.07134arxiv
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise2026-09-072609.07139arxiv
Vishing-Tactics-Bench: Forecasting Exploitation Trajectories in Voice Phishing Calls2026-09-072609.07151arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.