ALT This paper presents a dataset of 121,536 ground-reasons pairs across 86,464 rulings of the five civil chambers of the French Court of Cassation (2016-2025). An appeal on points of law cannot itself be appealed and often decides a case for good. Understanding how the Court rules is thus crucial and can help lawyers who draft those appeals. Inside a ruling, every ground of appeal (a distinct legal complaint against the appealed decision) has its own answer from the Court. This answer is called the reasons and it belongs to one of a few doctrinal families. Using a deterministic pipeline, we pair each ground with its reasons and attach the pair to its family, according to the established French taxonomy. We obtain a descriptive grammar of civil cassation that shows which grounds succeed, which legal texts they refer to, and how both evolve over the decade. We release the dataset, the code and an interactive consultation tool.

ALT Web agents increasingly serve the same user across repeated online tasks such as booking travel, shopping, and scheduling, so their long-term usefulness depends on how well they know the user's preferences. Passive memory and personalization methods cannot obtain preferences the user never reveals, and clarification methods that value a question by its benefit to the current task overlook the benefit of reusing the answer in later tasks. We study Active Preference Acquisition (APA): which missing preferences are worth the cost of asking? We define the Prospective Personalization Value (PPV) of a missing preference as its expected cumulative utility gain over future tasks minus the effort and disclosure-risk cost of asking, and select questions under a per-interaction budget. We characterize when cumulative reuse justifies acquisition despite insufficient single-task benefit, and evaluate this regime with an initial-profile diagnostic. APA computes the counterfactual gain of each candid

ALT Speculative decoding is a popular decode acceleration method. As such, it is particularly relevant to long-output generation, which requires an increasingly large KV cache. KV cache compression offers a way to constrain costs in long-context drafting. However, compression methods that focus on prefill information can lose relevance as the output length grows. We term this phenomenon decode staleness and show that it degrades draft model accuracy under selection-based KV cache compression. We introduce RIFT, a family of selection-based KV cache compression strategies that balance prefill information and recent generated tokens. We show that refreshing the KV cache selection during token generation significantly improves the drafter's quality at the cost of additional decode latency. To alleviate the refresh costs, we propose an adaptive KV refresh strategy that reduces the number of score calculations while retaining the drafter's quality. We further demonstrate how a compressibility-dr

ALT Reward models score responses for preference optimization, filtering and ranking, and pooling scores across prompts needs them to be comparable. Yet pairwise evaluation compares two responses to the same prompt, so any score component shared by a prompt's responses cancels and goes untested. We study this component by comparing between-prompt variation in model scores with the same variation in human ratings of the same responses. We propose a human-referenced audit, built from a between-prompt variance share, a sibling-rating regression and prompt substitutions, and apply it to eighteen released scorers and six matched training conditions. We find that scores cluster by prompt more than the ratings do: on HelpSteer2, six reward models have between-prompt shares of 0.34 to 0.64 against a human share near zero. Replacing the original prompt with a fixed instruction keeps substantial clustering but weakens agreement with prompt-level human ratings, so clustering alone does not show agree

ALT Content warning: this paper quotes slurs and hateful statements from published test suites; the racial slur among them is masked. Automated systems decide at scale which messages are harmful, and they decide unevenly. Classifiers label African American English as offensive up to twice as often as other English, the accounts of prominent drag queens can score as more toxic than those of white nationalists, and safety behaviour that holds in English collapses in low-resource languages. We argue that over-flagging and under-protection share one cause: deciding harm from vocabulary and surface form rather than from what a message does. We organise the evidence into seven failure modes and argue, as testable hypotheses, that harmful behaviours (a request for secrecy, a demand for payment, an attempt to isolate someone) travel across languages better than the words that express them. We propose an evaluation protocol that makes the gap between the best- and worst-served language communities

ALT Chunking strategies for retrieval-augmented generation are almost always evaluated on a static snapshot, yet the documents underlying a knowledge base continue to change. Because chunks are embedded independently, a boundary that moves after an edit forces unchanged text to be re-embedded. We measure this update cost on 120 pairs of adjacent Chinese and English Wikipedia revisions for three stateless chunkers (non-overlapping fixed-size, recursive paragraph-first, and content-defined chunking) under a strict byte-identical reuse rule and a frozen dense encoder. On the 116-article common-success pool, with frozen, length-calibrated parameters, fixed-size chunking recomputes 57-68% of its full new-version embedding-input workload, recursive chunking 38-56%, and content-defined chunking 43-54% (it failed on 4 of 62 Chinese articles), while at these parameters mean evidence recall under a fixed 2048-token retrieval budget differs by less than two percentage points within either language. A

ALT Single-document LoRA adapters have been proposed as units of knowledge to be merged and retrieved; yet open-book scoring, with the document in the prompt, can credit a document's own adapter (its specialist) for reading that document as readily as for holding it. Training one adapter for each of 150 Wikipedia articles on Llama-3.1-8B-Instruct, we find that open-book scores mostly measure a reading behaviour every adapter shares: a random adapter trained on another document recovers 82 % of the specialist's open-book advantage over the base model but only 2 % of its advantage on a cloze probe that asks for the same document's facts without providing the source text, a share we cannot distinguish from zero. Content does reach the weights, since the specialists beat the base model in cloze recall by 0.094, and the geometry of their updates follows the documents they read; yet, in a test of 30 queries, adapters chosen by weight-space proximity or text embedding are not distinguishable from

ALT Extraction pipelines ask language models for JSON that follows a schema, and the schema can set a minimum number of list entries. We ask what models do when the document holds fewer items than that minimum. Under a preregistered plan, we test eight open-weight models on 558 real documents from nine annotated datasets, with six more models on hosted services as a reference. Three findings stand out. First, models treat the count as a target: a minimum shown in the schema, but not enforced, raises the share of lists longer than the true count from 34.5% to 55.4%. Second, the padding is hard to catch, because most added entries are real text taken from the document; about half of them pass a check that each entry occurs in the source. Third, common fixes help only partly: a line saying fewer items are fine removes the effect on average but misses more true items, a count in prose ("up to k") also raises over-counting, an "N/A" option under an enforced minimum still leaves half the lists p

ALT Enthymemes are arguments that leave a premise or conclusion unstated, and they are a common persuasion device on social media. Because readers must fill in the missing part themselves, they often disagree on whether a text contains one. This paper asks how to detect and evaluate enthymemes when such disagreement is part of the task. On tweets about vaccination and immigration, each labeled by five annotators, F1 stalls around 0.67 for every fine-tuned model we train, regardless of data size, added features or label type. We therefore ask how these models should be evaluated instead, and propose metrics that compare predictions with the full distribution of annotator votes, together with a model that predicts this distribution directly and captures disagreement better at no cost in F1. We then ask what role discourse structure plays. Models learn to rely on explicit argumentative structure: they reliably recognize tweets without an enthymeme but rarely commit on tweets that contain one.

ALT Large language models (LLMs) often fail to utilise the context given in the input, resulting in hallucinations or a fallback to parametric knowledge. Context augmentation methods aim to improve model performance by modifying the input, from inserting filler tokens that add computational time to adding relevant content such as elaboration of a context during inference. However, these methods have been evaluated in isolation and only by their performance gains, leaving it unclear how they compare and whether they reliably improve performance. In this paper, we present an evaluation framework spanning five methods that differ in how informative the inserted content is and apply them at the sentence level across seven models spanning multiple sizes on three datasets. We find that accuracy gains are not always genuine improvements but undirected perturbations: the methods correct some predictions while breaking others, particularly when the inserted text allows only for more computational t

ALT Many language-model pipelines end in a closed-set decision, such as selecting a tool. Prompting a large language model for it is slow and order-sensitive. We ask how small an encoder for such decisions can be and whether it should read the options jointly or separately. In a three-seed study at 32 million parameters, per-option scoring beats joint scoring on a held-out sample of a 37-benchmark decision suite by 5.8 points of chance-corrected skill at matched optimizer steps and by 2.8 at approximately matched training compute; two external benchmarks agree, though not significantly on their unseen tasks. Crossing reader with initialisation shows that the advantage requires a reranker initialisation, whose query-candidate pair input matches per-option reading; from the raw encoder the two readers are indistinguishable. Per-option scoring needs 5 to 13 times more encoder passes: at most twice the median latency, but more than four times the mean. Of six released joint encoders (17 millio

ALT Language models (LMs) often exhibit successful cross-lingual transfer through continued (pre)training, still their underlying process remains unclear. One possibility is that LMs can leverage the evidence toward language-universal principles, namely, hierarchical structure, from a source language (L1) to a new language (L2), while many other non-linguistic explanations, e.g., improved initialization of position embeddings, can be potentially possible. In this study, to quantify the cross-linguistic transferability of linguistic evidence in cross-lingual LM training, we introduce a new experimental design, namely, a cross-lingual poverty-of-stimulus (CPOS) setting that ablates how LMs' hierarchical generalization in L2 can be led by structural evidence provided in L1. We contrast counterfactual L1 and L2 learning scenarios where the L2 corpus is ambiguous between linear and hierarchical grammar rules, while the amount of positive evidence for the hierarchical rule is controlled on the L

ALT Ophthalmic clinical decision support requires fast, accurate, and privacy-preserving inference, yet autoregressive large language models (LLMs) incur substantial latency and computational overhead for decisions among predefined actions. We therefore investigate a decision-oriented alternative to generative reasoning. Specifically, we first introduce RetiJev-Data, a source-grounded ophthalmology corpus comprising 78,158 clinical-decision and diagnosis questions derived from articles in PubMed Central and a MeSH vocabulary covering 531 eye diseases, and 50,074 guideline-grading questions spanning 11 grading systems, along with a 24,662-question evaluation benchmark. Based on this, we develop RetiJev, a family of 0.8B-9B decision models that directly score candidate answers without autoregressive decoding. Across all model sizes, RetiJev outperforms both a 27B LLM and the commercial Jev 1.13 decision model on guideline grading by 10.4-23.0 points. RetiJev-9B further achieves the highest a

ALT Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by reconstructing activations through a natural language bottleneck. However, it remains unclear how well these methods generalize beyond the setting they were trained for. Here, we study this question for NLAs along four closely related questions: (i) Do NLA verbalizations exhibit compositional structure with respect to their input? (ii) Do NLAs generalize to finetuned versions of the model they were trained for? (iii) Can NLAs recover finetuning objectives in model diffing? (iv) Can NLAs be specialized for model diffing? Across four models from three families, our experiments provide evidence supporting a largely positive answer to all four questions. Specifically, verbalizations of composed analogy activations mostly name the target while rarely mentioning the subtracted word, and an NLA can be reused o

ALT With external tools, large language models (LLMs) can tackle complex tasks through sustained environmental interaction. LLM-based agents are therefore increasingly used to tackle complex long-horizon tasks in real-world environments. However, these tasks involve sequential, interdependent decisions and changes in environmental states. Early execution errors affect subsequent interaction histories and environmental states, and their effects accumulate along the decision chain. To address this challenge, we propose Reflection-Guided Policy Optimization (ReflectPO), a reinforcement learning framework for autonomous error recovery in long-horizon tasks. ReflectPO comprises two core components. The first is Reflection-Guided Sampling. We use branch differences and repeated visits in interaction trajectories to construct hints for error recovery. The second is Tree-Structured Credit Assignment. We organize sampled trajectories into trees and assign action-level credit using parent–child rewa

ALT Silicon sampling generates survey respondents by having a large language model (LLM) answer a survey as a person with given demographic attributes, and the resulting synthetic populations are increasingly used in place of human ones. Existing evaluations focus on individual-answer accuracy, per-question answer distributions, and correlations across questions. None of these compares the respondents themselves, so a generator whose respondents have combinations of answers found in no human respondent can still score well if it reproduces every answer distribution. We propose the respondent coverage gap (RCG), which represents each respondent as a point defined by their complete answer profile and measures how far each human respondent is from the nearest generated one, relative to the distance between human samples. On two US social surveys, all six LLMs we evaluate leave human respondents uncovered, and under our main settings, they fall behind a baseline that samples each answer indepe

ALT Cyberbullying involves behavioral and contextual patterns beyond isolated abusive messages. However, existing approaches remain fragmented across content detection, semantic representation, and network analysis, with limited interpretable perpetrator representations, multi-scale structural modeling, and explanations of behavior-driven similarity and influence propagation. These limitations hinder the identification of persistent perpetrators, characterization of behavioral communities, and assessment of potentially influential users. This paper proposes Ontology-Driven Cyberbullying Behavior and Network Analysis (ODCBNA), a perpetrator-centric framework integrating requirements-driven ontology design, knowledge graph construction, behavioral modeling, community analysis, and influence modeling. Using the Bengali Contextual and Diverse Cyberbullying (BenCoDiC) corpus as a use case, ODCBNA identifies 1,063 users with at least three bullying comments or replies as perpetrators and represe

ALT Nepali-English code-switched conversational speech presents severe challenges for automatic speech recognition (ASR), chiefly through script confusion (inappropriate mixing of Devanagari and Latin orthography) and elevated error rates at language switch points. Supervised fine-tuning (SFT) can adapt multilingual foundation models, but human code-switched audio is expensive to collect and annotate. We curate a new benchmark of 13,044 spontaneous podcast utterances (15.45 h total; 10,214 test, 2,830 dev), audited and verified to eliminate machine translation leakages and acoustic loops. We investigate a two-stage synthetic-to-real adaptation framework: Stage 1 applies SFT on 0.95 h of speech synthesized via a multi-speaker, dual-engine TTS pipeline; Stage 2 explores Group Relative Policy Optimization (GRPO) with transcription and script rewards. We find that synthetic SFT provides the primary cross-domain transfer to spontaneous human speech, reducing Mixed Error Rate (MER) from 23.40% t

ALT Ambiguity is a central feature of natural communication: a sentence, image, or sound may remain underspecified until evidence from the other channels is considered. Yet current multimodal benchmarks mostly test perception, recognition, or reasoning over already determinate inputs, leaving unclear whether omni-modal large language models can resolve ambiguity distributed across text, vision, and audio. We introduce TRIAD, a benchmark for omni-modal ambiguity resolution. Each item is a text–image–audio triplet paired with a question and a set of answer options, and is constructed so that the full triplet determines a unique answer while removing any one modality makes the set of consistent options non-unique. TRIAD contains 327 hand-written queries in 86 scene groups and covers 18 ambiguity categories across the three modalities. Evaluating 14 omni-modal systems reveals that strong item-level performance does not translate into robust scene-level disambiguation: the best model still trai

ALT LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce TutorCaseBench, a benchmark that grounds AI-tutor evaluation in qualitative case studies from pedagogy, educational psychology, and special education. Our pipeline converts documented student categories into case-specific scenarios, tutor-student dialogues, and rubrics grounded in source evidence. The benchmark contains 923 dialogues across five challenge types, evaluated through open-ended response generation (1,560 items) and multiple-choice selection (2,537 items). Across 11 state-of-the-art LLMs, even the strongest model satisfies a rubric criterion in only 55.8% of open-ended cases, while models are better at selecting appropriate strategies than generating situated responses. These results reveal a gap between intervention recognition and context-specific adaptation, especially for open-weight models. All