arXiv_CL
-
AfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM Agents
2026-10-22 14:41:36Ehsan Saleh, Roozbeh Nahavandi, Sama Salarian, Raef Bassily, Andrew PerraultAbstract
Many LLM agents maintain external persistent memory and derive additional state from past interactions, such as summaries. Deleting an original memory record therefore need not remove information carried by its descendants. We introduce AfterDeleteBench, a controlled behavioral audit for this failure mode in fixed-weight LLM agents. For each synthetic secret, we compare an exposed-then-deleted agent with an otherwise matched agent that was never exposed to the secret, allowing post-deletion recovery to be attributed to the original exposure. In our primary setting, a single query recovers the deleted secret from Qwen2.5-7B-Instruct in roughly two thirds of cases, while matched never-exposed controls have zero recovery. Crucially, recovery does not require a surviving verbatim copy: when the complete secret string is absent and only separately stored components remain under a public composition rule, exact reconstruction succeeds in 62-99% of cases across Qwen, Mistral, and Phi-3. We also show that the response interface is part of the measurement system: target-bearing replies can be scored as failures when the requested format and parser are misaligned. Finally, we separate reconstruction from write-back and fresh-session recall. Provenance-aware closure eliminates observed recovery in the tested positive-baseline settings, whereas an exact-literal write filter blocks reinsertion but cannot erase information already present. Together, these results show that source deletion should be evaluated behaviorally at the level of the agent and its memory system, not only as a storage operation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31366
PDF
-
CrisiLangs: A Multilingual Resource for Crisis Warning Generation
2026-10-22 14:37:09Giacomo Gonella, Stefano Menini, Marco GueriniAbstract
Communicating with the public during an emergency entails issuing warning messages promptly. In Europe, it often requires producing them in more than one language. Recent work has shown that language models can be trained to generate warning messages as a crisis unfolds, but the available data covers only English. To fill this gap, we present CrisiLangs, a multilingual extension of CrisiText (an English dataset of crisis events paired with warning messages written according to expert communication guidelines) to Italian, Bulgarian, German, and Greek. Expert native speakers translated the warning messages of 1,000 events drawn from 411 scenarios, for a total of 5,000 event-message pairs across five languages. We test the resource to fine-tune a multilingual model on all five languages jointly, with and without the emergency guidelines in the prompt, and compare it with a zero-shot baseline. The fine-tuned models outperform the baseline on ROUGE-L, BLEU and BERTScore in every language and configuration. In a human preference study, low decoding temperatures receive the most preferences in all five languages and in both configurations, while the effect of the guidelines varies by language.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31356
PDF
-
SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
2026-10-22 14:08:59Yifan Yuan, Yancheng Zhu, Zuoyu Zhang, Xiaogang PengAbstract
Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity Knowledge Graph (MEKG) encoding method-level follow-on, competition, and shared-resource relations. The graph supports core-paper discovery, retrieval, hybrid outlining, and evidence-gated narrative synthesis. We evaluate retrieval, semantic edges, citation grounding, collection coverage, and generation-stage components. In a controlled seven-method equal-budget benchmark, MEKG-anchored fusion balances recall and structural density, with an independent co-citation check. In a separate archived graph-native diagnostic, graph-aware retrieval nearly doubles recall over flat lexical baselines across eight runs (p = 0.004). A semantic evidence gate achieves AUC = 0.75. Audits of 160 generated sentences find 80.6% anchored-or-partial citation support. Human adjudication of 108 stratified semantic edges finds 68.5% supported-or-partial relations (binary-support Cohen's kappa = 0.64), with improves strongest (80.6%) and extends weakest (52.8%). A SurveyBench-facing collection probe reaches mean reference coverage of 0.521 across four topics with an eight-paper budget. Same-backend Qwen diagnostics on a 30-paper/74-relation graph show reduced organization signals when hybrid outlining is removed. Concurrent-system comparisons provide bounded context rather than matched-backend end-to-end evidence. The results position MEKG as an auditable structural layer for typed diagnostics, relation-specific filtering, and controlled survey generation. Code and artifacts: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31317
PDF
-
When LLMs Forget What They Believe: Characterizing State Integrity Collapse in Long-Horizon Dialogues
Abstract
Large language models can repeat an instruction while failing to keep obeying it. We study this recall-compliance dissociation in long-horizon dialogue and define State Integrity Collapse: a model preserves a stated constraint in memory but stops applying it to later turns. We introduce StateTrack-Bench, a controlled suite of conversations covering numerical, format, role/persona, factual-memory, and logical-rule constraints. Across seven provider-pinned model snapshots and five dialogue-depth probes, strict joint retention ranges from 62.4% to 100.0%, with degradation concentrated in symbolic constraints and in one especially brittle model. A forked recall audit shows that 88.6% of observed failures are behavioral-drift failures rather than ordinary forgetting; excluding the brittle outlier preserves this diagnosis (84.4% of failures). Extended evaluations at depths up to 50 turns confirm that the dissociation persists beyond the core benchmark, while Structured State Anchoring recovers up to 24.4 points on immutable constraints. The results show that reliability cannot be inferred from single-turn instruction following alone; evaluation must track whether remembered constraints remain operational as dialogue state grows. Code and artifacts are available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31314
PDF
-
Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation
2026-10-22 14:04:07Hongcan Guo, Yian Zhao, Feng Wang, Shen Nie, Guoqiang Wei, Yan Zeng, Hengshuang ZhaoAbstract
Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiveness depends on what the latent space compresses and how the discrete generator uses it. We propose Cola2, a framework that jointly studies continuous semantic compression, the balance between reconstruction and generation, and continuous-discrete co-adaptation. Cola2 dynamically segments text into semantic spans, controls the compression rate through auxiliary-loss-free negative feedback, and combines reconstruction and generation supervision to learn compact, predictive latent representations. A block-causal masked diffusion decoder is trained with clean, noisy, and dropped latent conditions, while classifier-free guidance adjusts the balance between semantic reconstruction and autonomous generation. Token-prediction gradients update the encoder through the latents, whereas Flow Matching prior learning is decoupled from representation learning by stop-gradient. During inference, generated text is re-encoded under a fixed span layout to keep the latent history consistent with the actual text context. Experiments on five downstream tasks with about 210 billion training tokens validate the core designs and show competitive, unsaturated scaling. With 346.03 billion source tokens, an unconverged checkpoint reaches a 60.10 average across eight tasks and surpasses Llama-3-8B on HellaSwag and StoryCloze despite its reported pretraining budget being over 43 times larger. These results demonstrate the potential of continuous-latent hierarchical language generation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31305
PDF
-
The Value of Memory in Language Agents
2026-10-22 14:01:31Zehao Lin, Erenkai Zhu, Helan Hu, Xixuan Hao, Chunyu Li, Kai ChenAbstract
Memory enables language agents to carry useful distinctions from past experience into future decisions. Its value depends on which distinctions survive, whether a bounded agent can use them, and what can be recovered or revised as demands evolve. We develop a decision-theoretic framework that follows this value from raw history through persistent state, operational use, and costly recovery and revision. Original and retained value are expressed in units of avoided task loss; risk-cost frontiers describe attainable recovery and preservation across uses. Unknown demand yields value profiles, while interactive feedback changes the distribution of future work. A cost-aware simulation condition and five minimal counterexamples expose the roles of information timing, retrieval access, component interaction, feedback and demand uncertainty. In particular, a pointer with zero mutual information about the answer can still reduce the cost of exact recovery. Diagnostics on LoCoMo, a two-project update task and longitudinal cases exhibit failures of preservation, use and measurement. At fixed retrieved evidence, a saved ledger changes subsequent answers; at fixed agent outputs, an evaluator revision changes scores. The framework connects these distinctions to operational risk bounds and testable principles for allocating memory, preserving recovery options and revising evidence dependencies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31303
PDF
-
On the Behavioral Traits of LLM Agents
2026-10-22 14:01:08Haokai Zhao, Jie Gao, Yunze Xiao, Xintao Wang, Weihao Xuan, Aditya Joshi, Mark Dredze, Jen-tse HuangAbstract
Users increasingly describe different AI agents as distinct colleagues to work with. AI personality research aims to quantify such impressions by attributing human- like "traits" to agents. However, existing measures fall short: models' self-reports (S-data) diverge from their actual behavior, while informant ratings from LLM judges (I-data) are costly to scale and cover few everyday scenarios. In this paper, we propose A-B-D to infer traits bottom-up from behavioral data (B-data), namely how agents act on their environment and communicate with users, as recorded in existing trajectories. From 345,667 real-world trajectories spanning 80 models, 12 tasks, and 50 harnesses, we extract 318 candidate features that capture both the actions an agent takes at each step (functional) and the language accompanying them (linguistic). We retain only features that show instance-level stability, cross-task consistency, and model discriminability. Factor analysis of the remaining 79 features uncovers six stable, model-attributable factors, two functional and four linguistic. For example, Claude-Sonnet-4.6 and Kimi-K3 exhibit the most planfulness, whereas GPT-5.5 and GPT-5.6 are the least energetic. Moreover, we quantify the "knowledge-action gap" in the wild: these factors correlate only weakly with self-reported Big Five scores, even for conceptually matched pairs such as extraversion and energetic (r = 0.07, p = 0.58). Our work offers a new lens for understanding AI personality, with implications for users, developers, and researchers from both computer science and social science.
Abstract (translated)
URL
https://arxiv.org/abs/2609.32776
PDF
-
CoWriter: Guiding Methodological and Synergetic Human-LLM Co-Authoring
2026-10-22 13:45:47Shmuel Amar, Benjamin Lieber, Ori Shapira, Debanjana Kar, Sebastian Maximilian Dennerlein, Yufang Hou, Ido DaganAbstract
While LLMs have transformed text generation, standard chat-and-canvas interfaces often reduce human authoring to quite passive supervision, causing review fatigue, over-reliance on AI, and the sidelining of the human role in long-form, source-grounded writing. Prior systems typically address isolated writing phases, leaving comprehensive end-to-end human-LLM collaboration largely unexplored. In this paper, we introduce CoWriter, a proactive agentic scheme that adapts expert human (co-)authoring methodologies from cognitive science to flexibly steer the entire writing workflow while actively encouraging the user to engage. In an exploratory user study, compared to a standard LLM baseline, authors using CoWriter better expressed their perspectives and maintained a higher sense of document ownership, supported quantitatively by $2.2\times$ more successful agent engagements. Furthermore, external reader judges rated the resulting texts higher in "human touch" qualities like storytelling and integrating unique personal experiences. Overall, our results demonstrate that proactively engaging users through established human practices is beneficial for effective LLM-supported co-authoring, providing useful methodologies, techniques and insights for future research on collaborative agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31277
PDF
-
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
2026-10-22 13:43:33Yijiang River Dong, Zexue He, Cheng Yu, Tiancheng Hu, Michael J Ryan, Jan Batzner, Zheng Hui, Shaolong Wu, Orestis Papakyriakopoulos, Alex Pentland, Nigel Collier, Jiaxin PeiAbstract
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer. Existing evaluations assess memory capabilities without directly establishing whether memory use benefits the user. To study this gap, we collect approximately 1,000 pairwise judgments from 87 participants using their own ChatGPT queries and personal memories. We find that memory-conditioned responses are not consistently preferred over responses generated without memory and in some cases, users strongly prefer the latter. Automatic evaluators also show limited agreement with users and favor memory-conditioned responses substantially more often than users do. Motivated by these gaps, we introduce a memory-aware reward model that learns from user judgments, achieving 72.8\% preference prediction accuracy and outperforming the existing baselines. Our findings motivate evaluation and optimization objectives that align memory use with the preferences of the people whose information is being used.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31272
PDF
-
Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing
Abstract
Language models now routinely grade other language models. If post-training makes a model's writing more predictable, it may also teach the same model, as a judge, to reward predictable writing. We test this directly. We follow two open 7-billion-parameter model families, OLMo-2 and Zephyr, from their base models through supervised fine-tuning (SFT) and direct preference optimization (DPO), and measure every stage as a writer of short stories and as a judge of story pairs. As writers, the models drift as feared. Each family's trained model finds its stages' stories more familiar in the order base, SFT, DPO, in all ten prompts, and a model from the other family finds the trained stories 7.0 to 9.2 percent (OLMo-2) and 24 to 25 percent (Zephyr) less surprising per token. As judges, they barely move toward predictable writing. Asked which story is better, a question every judge passes a competence check on, no trained judge's preference for the more predictable story grows by as much as one point of pick probability at its estimate. A one-sided 95% upper bound on that growth is about 5 points on the widest pairs. Training instead makes judges more swayed by story length and by display order, and it breaks "more creative" as a question. Trained judges no longer reliably prefer a story to its own words in scrambled order. For these two families, the practical hazard in a small trained judge of creative writing lies in these measurable habits.
Abstract (translated)
URL
https://arxiv.org/abs/2609.32196
PDF
-
A Systematic Comparison of Search Space Complexity and Efficiency for Time-Synchronous End-to-End ASR Models
2026-10-22 13:35:50Simon Berger, Larissa Kleppel, Ralf Schl\"uterAbstract
Search is a central component of Automatic Speech Recognition (ASR) systems and has been deeply investigated for classical ASR modeling based on Hidden Markov Models (HMMs). However, in work on current sequence-to-sequence ASR architectures it is often simplified to a small fixed-size beam search without external Language Model (LM). In this work, we present a comparative analysis of search space complexity and efficiency for Connectionist Temporal Classification (CTC) and neural transducer models under different pruning strategies and LM configurations. We show that these end-to-end (E2E) models work with a small search space most of the time but exhibit large temporary peaks in hypothesis count during periods of uncertainty. Score-based pruning dynamically adapts the search to model uncertainty, leading to a significantly lower Real-Time Factor (RTF). Our results highlight the limitations of search with low fixed-size beam pruning and provide practical guidelines for efficient search in E2E ASR.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31259
PDF
-
IndoNutriQA: An Indonesian Clinical Nutrition Question Answering Benchmark
2026-10-22 13:34:29Tirana Noor Fatyanosa, Ummu Ditya Erliana, Mahendra Data, Muhammad Nurwegiono, Eleazar Tadeo Eman, Alham Fikri AjiAbstract
Clinical Question Answering (QA) underpins Clinical Intelligent Decision Support Systems, but progress is severely limited for low-resource languages such as Indonesian by the absence of public domain-specific data. We introduce IndoNutriQA, an expert-curated Indonesian clinical QA benchmark of 911 question-answer pairs built from real clinical-nutrition reports. Rather than a large-scale training corpus, it is positioned as a high-quality evaluation resource: every pair is grounded in a clinically relevant context, enriched with structured metadata (anthropometric assessment, medical diagnosis, document provenance, chunk segmentation). Eight standardised question types following the Nutrition Care Process (NCP), including the Problem, Etiology, Sign and Symptom (PES) diagnosis statement, are answered for every report, which was written by a graduate-level dietetic intern, by one of three nutritionists. Answers are free-form clinical prose rather than extractive spans, and an expert validation study finds 6-10% of reference answers contestable. The dataset supports generative, extractive and retrieval-augmented QA as well as zero- and few-shot LLM evaluation. We report fine-tuned baselines (IndoBERT variants, mT5, RAG) with 5-fold cross-validation, learning curves and bootstrap 95% confidence intervals, and benchmark eight contemporary LLMs zero- and five-shot. We further calibrate our LLM-as-judge rubric against three expert raters (one RD, two nutritionists), finding it human-comparable on factuality and completeness but unreliable on clinical safety, and a human error analysis shows it misses unsupported content that the raters identify. IndoNutriQA is released to foster research in Indonesian clinical NLP and nutritional decision support.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31256
PDF
-
Predicting Music Valence and Arousal via Textual and Multimodal In-Context Learning in Large Language Models
2026-10-22 12:49:14Chi-En Dai, Chih-Pin Tan, Yi-Hsuan YangAbstract
While arousal can be reliably predicted from musical audio, emotional valence remains difficult to model due to its subjective and context-dependent nature. In this work, we investigate the potential of in-context learning (ICL) with large language models to advance continuous valence and arousal prediction. Rather than predicting emotion scores directly, our framework leverages contextual demonstrations from an auxiliary dataset to refine the initial predictions produced by a small, task-specific base model. We systematically evaluate a text-based ICL variant using lyrics and generated audio captions, alongside a multimodal variant that incorporates raw audio signals. Using the entire MER60 dataset strictly as a held-out test set, our experiments demonstrate substantial performance gains, particularly for valence. Text-based ICL improves the valence $R^2$ from 0.110 to 0.427 with 80 demonstration shots, while the multimodal variant achieves 0.346 with only 10 shots. These findings suggest that training-free ICL offers an effective inference-time strategy for current language models to predict continuous music emotion.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31202
PDF
-
Investigating Multi-Cultural Value Selection Biases in LLMs
2026-10-22 12:46:22Siddhesh Pawar, Arnav Arora, Dustin Wright, Dirk Hovy, Isabelle AugensteinAbstract
Large language models (LLMs) serve users whose cultural identities are multi-layered, yet cultural evaluations commonly reduce identity to one label. In this work, we study LLMs under simultaneous identity cues, with a country persona in the system prompt and a second identity signaled in the user turn, either by naming a country (explicit cue) or through the query language (implicit cue). We test World Values Survey (WVS) multiple-choice probing and open-ended sociopolitical generation. In multiple-choice probing, language cues shift answers about three times more than explicit cues but away from the associated country's distribution, and explicit cues do not consistently move answers toward the named country. Across 1.6 million open-ended responses, naming a country closes 30-44% of the gap to the model's own responses for that country, and explicit cues produce more differentiated value changes than language cues. Our results suggest that country and language cues should be evaluated as distinct signals rather than interchangeable proxies for culture.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31199
PDF
-
When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions
Abstract
Metadata-conditioned generation is often framed as a data-to-text task in which additional input fields should improve grounding. Museum description generation challenges this assumption because catalogue records are heterogeneous, partially visual, and unevenly documented across geographic regions. We study how metadata composition shapes the generation of artefact descriptions through a two-phase framework. Phase 1 analyses natural metadata variation in a large museum collection, where field count, field type, image availability, and Place co-vary. Phase 2 introduces controlled field probes that hold object identity fixed while varying metadata quantity, field type, and image access. Our results show that metadata quantity alone does not explain generation behaviour. Field type determines whether models ground, omit, or infer information, while images can both support visual grounding and increase unsupported interpretation. More broadly, our findings show that metadata-conditioned data-to-text evaluation should assess field- and claim-level support, rather than relying only on aggregate input coverage or reference similarity.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31193
PDF
-
Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness
Abstract
LLM-as-a-Judge evaluation is increasingly applied to multilingual tasks, yet prompting strategies such as Chain-of-Thought and Role Conditioning are recommended based solely on English benchmarks. Whether their effectiveness transfers across judge models and languages remains unknown: prompt-sensitivity studies are largely English-centric, while existing multilingual judge studies fix the prompt template. In this work, we address this gap by measuring this interaction through a benchmark of 9 prompting strategies, 4 open-weight judges, 27 languages, and 4 tasks across 13 datasets, yielding over 1M pointwise scores on gold-reference outputs, validated against human judgments. We find that prompting strategies are not transferable: the choice of the judge model dominates the choice of prompting strategy, strategy effects reverse direction across judges, and stability degrades in low-resource languages, where these effects are concealed by aggregate reporting. These findings show that prompting effects in multilingual evaluation are conditioned on the judge, task, and language. Consequently, prompting strategies should be validated for the intended evaluation setting, and cross-study comparisons should account for both judge and prompt configuration.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31172
PDF
-
Prompt Sensitivity in Tool-Augmented Model Comparisons
2026-10-22 12:07:01Mateusz Modrzejewski, Tomasz RadzikowskiAbstract
Language models are compared on question-answering benchmarks that pose each question in one wording, and a reworded question can change which of two models scores higher. We ask whether giving the models tools makes such comparisons more stable. An accuracy gain cannot answer this, because tools change several steps between the question and the scored answer at once. We propose a matched protocol that separates those steps: the answer readout, reasoning, the decision to call, the tool's answer, and the report supplied without a call. We apply it to six open models in five domains under five wordings. We find that tools raise accuracy where a program answers the question and widen the wording sensitivity of many pairwise comparisons. The widening follows how often a model calls, and call frequency follows the wording for some models and not others. It also depends on the interface and the instructions: a native tool-calling interface and a second tool description leave no detected widening in molecules, and sensitivity persists where tools return intermediate results. These findings show that deterministic reports do not guarantee stable comparisons. We recommend reporting call frequency and comparison stability under several wordings beside accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31148
PDF
-
Mixing Matters: Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering
Abstract
Long-context models often use answer-bearing evidence less effectively when it appears away from a prompt boundary. We compare this position bias across Transformer, state-space, and hybrid Mamba architectures by moving one gold document through a fixed set of nine distractors. The evaluated Transformers show a beginning advantage that the evaluated state-space models lack, while both families favor evidence near the end. A matched pure-versus-hybrid Mamba comparison points in the same direction but remains statistically uncertain. The family difference appears among models that can answer the task. Transformer primacy reappears on synthetic retrieval, where state-space ceiling prevents a family comparison. A corpus swap within one state-space architecture changes overall accuracy without a detectable change in curve shape. Prompt changes can create or nearly remove a beginning advantage. Position remains decodable across architectures even when response curves differ, and attention concentration near initial tokens covaries with beginning sensitivity in the tested Transformer family. These exploratory results show that effective context use depends on the evaluated architecture family, capability, task, and prompt, without isolating the sequence mixer as the sole cause.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31135
PDF
-
Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory
Abstract
Our previous analysis found that a model's native hashed N-gram table is where continual updates disturb the base least, but its writes needed backpropagation and changed the pretrained table. We present Delta N-gram, a forward-only write path into that table. The pretrained table T^0 is never modified. Evidence is written into a sparse patch \Delta on the rows it addresses: a 4.1M-parameter writer emits a target and a gate per (position, hash head) event, and a block-averaged delta rule keeps each row a convex combination of its old value and the gated targets. The writer is trained offline on raw text with the pretraining objective; at use time writing takes forward passes only, and clearing \Delta restores the original model. A 0.6B prototype trained to answer questions keeps 16/16 facts after a second write; online gradient writes keep 2--4/16. We study two writers: a plain writer that encodes evidence with the T^0-only model, and a delta writer that reads its current memory while encoding. On Qwen3.8-Flash-Next, the plain writer's memory is document-specific: on 64 held-out news events it lowers continuation NLL by 0.068 nats/token against empty memory and by 0.024 against another document's memory, and 0.063 and 0.013 after 16 intervening articles. The delta writer's memory is more document-specific and keeps more of it under distraction (70% vs 54%). Over 35,000 writes on our previous seven-task chain both writers stay stable and the delta writer drifts less (layer-2 math drift 176% vs 188%); later accuracy changes by -0.26/-0.52pp (-7.29pp for gradient updates) and small-k_i drift is 17.9/17.5% (39.2%). Acquisition is negative, and general-input drift reaches 32.8% (20.75%): format rows read by every example grow to 4--12 times their pretrained norm. Zeroing eight such rows removes over 98% of layer-2 drift on math inputs, together with their NLL gain.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31125
PDF
-
A Grammar of French Civil Cassation: A Ground-Level Dataset and Tool
2026-10-22 11:30:50Avrile Floro, Tamara Dhorasoo, Nils Holzenberger, Thomas Le Goff, Tiphaine Viard, Maria BoritchevAbstract
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.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31116
PDF
