arXiv_CL
-
GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models
2026-10-20 16:15:02Ziyong Wang, Yupei Lin, Runxuan Huang, Liang Lin, Dongyu Zhang, Guangrun WangAbstract
General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide action remains underexplored. We investigate this question using contact-rich manipulation as a representative testbed, examining tactile understanding as a concrete instance of this broader capability. Contact-rich manipulation requires interpreting tactile feedback and adjusting actions after obstruction. Existing learned tactile policies acquire these capabilities through specialized pretraining and per-task optimization, with substantial data and training costs. We present GPT-as-Tactile-Policy, which summarizes expert demonstrations into task guidance and tactile references for contact assessment and corrective action. GPT-6-Astra combines this context with multimodal observations and interaction history to generate control commands and adjust actions through contact feedback. Without additional robotics-specific pretraining or per-task policy fine-tuning, our method achieves 93.8\% mean success across five UniVTAC tasks. Overall performance is comparable to state-of-the-art policies, with higher success on selected tasks. On Insert Hole, tactile feedback improves success from 31\% to 99\%. Execution analysis further demonstrates contact-guided probing and correction, supporting manipulation progress through explicit expert experience and online feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28457
PDF
-
MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious Traditions
2026-10-20 16:11:21Nikita Ganziuk, Innokentiy S. Humonen, Ilya Makarov, Pavel LebedevAbstract
We present a tool for the comparative study of mythological and religious texts. Traditional manual analysis is highly labor-intensive and difficult to scale. To address this, we use neural language models to embed texts into a shared semantic space, so that users can find semantic parallels across cultural traditions in an interactive interface. Embedded fragments form distinct semantic structures whose coarse geometry aligns with well-documented historical relations between traditions. We quantify how much of that geometry is already explained by lexical overlap and by proper names. The current system is available at this https URL, and the installable package is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28452
PDF
-
Compute-Optimal Scaling Laws for Spiking Language Models
2026-10-20 15:59:21Dan Saunders, Benjamin Ren, Catherine HeAbstract
Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking language models is uncharacterized at scale. We present the first Chinchilla-style IsoFLOP scaling study of a spiking language model, sweeping SpikeGPT-family models (RWKV backbone) from width 384 to 1536 across compute budgets from $3\times10^{17}$ to $10^{19}$ FLOPs on FineWeb-EDU. We report two findings. First, the compute-optimal frontier is $N_{opt} \propto C^{0.56}$, close to the 0.50 that Hoffmann et al. report for dense Transformers, so spiking does not change how parameters and data should be traded off under a compute budget. Second, against non-spiking RWKV and Transformer baselines trained the same way, the loss gap splits into a backbone cost of about 0.16 nats that does not change with compute and a spiking cost that falls steadily with compute, from 0.34 to 0.23 nats over our range. These results give the first compute-optimal recipe for spiking language models and quantify the accuracy cost of their sparsity.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15146
PDF
-
When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
2026-10-20 15:40:54Jinghui Zhang, Lang Gao, Zongfang Liu, Ruihong Zeng, Zirui Song, Rui Yan, Kentaro Inui, Xiuying ChenAbstract
Precisely reproducing a target span verbatim within a long context is a fundamental capability test for LLMs: even when the target string is present in context, models often still drift within the span or fail to stop correctly, revealing limitations in source grounding and boundary control. This capability has broad practical relevance. For instance, code generation often requires embedding sensitive strings such as API keys exactly as they appear in context. In this work, we construct a benchmark to test exact span reproduction ability across contracts, scientific literature, code, and random sequences, and find that current models still make surprisingly frequent errors. To address this, we propose CopyGen, a lightweight copy-constrained plugin for frozen LLMs that turns copying from a byproduct of next-token prediction into a controlled process. Our key idea is to decompose copying into three distinct decisions: when to copy, how far to copy, and when to stop. Concretely, CopyGen first determines whether to enter copy mode, then predicts a tentative copy length, and finally verifies the generated span token by token. During verification, we adaptively adjust the logits of copy continuation tokens to incentivize or suppress continuation, and emit only the longest valid prefix. Across three LLM backbones and four benchmark tasks, CopyGen improves average exact match by 35% relative without model finetuning, and integrates seamlessly with SFT to further improve it by 4%, while substantially accelerating generation. These results suggest that reliable exact copying is not something LLMs obtain for free, but a decoding-time control problem that requires explicit modeling. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28393
PDF
-
CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied Agents
2026-10-20 15:33:20Youmna Farag, Svetlana Stoyanchev, Simon Keizer, Mohan Li, Rama DoddipatlaAbstract
Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety reasoning at two levels: (1) an action-level dataset that tests whether a single action is safe given its environmental context, and (2) a plan-level dataset that evaluates whether agents can generate safe long-horizon plans for complex hazardous household tasks. CAPSafe models safety conditions where hazards are situational (inferred from object properties), multiple hazards can co-occur within the same environment, and each is annotated with a relative severity level for fine-grained analysis. Evaluating nine closed and open-source LLMs reveals a substantial gap between hazard recognition and safe long-horizon planning. Several models achieve high accuracy in recognizing unsafe actions (exceeding 90% in the best cases), yet safe long-horizon planning remains substantially harder. Gemini-3-pro achieves the highest safe success rate (78.19%), while other models remain below 65%. These results highlight that robust safety reasoning over long action sequences remains an open challenge.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28381
PDF
-
Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design
2026-10-20 15:32:52Gaotang Li, Bhavana Dalvi Mishra, Yifei Ming, Yanfei Chen, Zhongying CuiZhu, Lesly Miculicich, Long T. Le, Rui Meng, Chun-Liang Li, Hanghang Tong, Chen-Yu Lee, Tomas PfisterAbstract
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different execution strategies. In this work, we introduce Object-Oriented Harness (OO-Harness), a harness optimization framework that evolves a hierarchy of executable harness classes using object-oriented design. During training, an evolution agent uses execution records to create a family of specialized harnesses, each implemented as a subclass of the base or an existing specialized harness via inheritance. At test time, a harness router uses routing lessons accumulated during training to select a specific harness for each task. Across three long-horizon benchmarks spanning business workflows, workspace tasks, and tool use, OO-Harness achieves the best performance among the compared methods, with an absolute improvement of up to 15% over the base. Extensive ablation studies examine the contributions of its core components.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28380
PDF
-
DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge
2026-10-20 15:07:19Atharva Thakur, Abulhair Saparov, Bruno RibeiroAbstract
Reliable retrieval-augmented generation (RAG) requires recognizing when neither retrieved documents nor parametric knowledge supports an answer. We introduce DeclineCraft, a dynamic abstention benchmark whose unanswerable questions target Minecraft feature additions after a corpus cut-off, with audits of possible parametric exposure. Later cut-offs support evaluation of future models. Across 27 LLMs, we measure Correct Abstention Rate (CAR; how often models acknowledge insufficient knowledge on unanswerable questions), Answerable Attempt Rate and Answer Accuracy. We find that (1) single-shot retrieval significantly raises CAR in 38 of 40 configurations (model and thinking setting) versus no retrieval. (2) Iterative RAG, in which the model self-assesses its context and can request up to two further retrieval rounds, significantly lowers CAR versus single-shot RAG in 30 of 40 configurations (mean 46.4%), with little change in Answer Accuracy (68.5% to 69.3%). Adding query rewriting and reranking to hybrid (dense & sparse) retrieval lowers CAR for all 12 models tested. (3) Larger models answer more accurately (Spearman $\rho = +0.60$ with total parameters), but neither model size nor release date shows a significant association with CAR. (4) Without retrieval, enabling thinking on the same weights lowers CAR significantly for 8 of 13 models (by 14% points on average), and the responses shift from acknowledged uncertainty to premise denial.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28340
PDF
-
Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
2026-10-20 14:52:57Masahiro Kaneko, Hiromi Arai, Timothy BaldwinAbstract
Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy risk if exposed. We ask how consulting memory during dialogue changes what users go on to say, and thus what the memory comes to reveal. In multi-session simulations, a simulated user with 24 personal attributes talks with a support agent that does or does not consult memory, and in both settings attributes are inferred from the full accumulated record. Across four support models, memory raises response quality but also empirical leakage, the share of attribute values correctly inferred from the record, by a margin that widens over sessions. The cause is a loop in ordinary, non-adversarial assistance. Memory-conditioned responses carry earlier values forward, often as presuppositions, and users affirm them or leave them uncorrected, so that cues and the agent's own guesses become recorded values. The loop reinforces itself, and removing the agent's mentions of an attribute lowers its later disclosure about twice as much as single-turn effects predict. Users cannot leave it on their own, since correcting a value discloses the attribute, declining to discuss it shifts later predictions toward sensitive values, and incorrect values left in place become entrenched. The loop is best weakened at the agent's response. Instructing the agent not to state or presuppose attributes brings leakage to about the no-memory level while keeping most of the quality gains, whereas filtering or anonymizing what users say or what is stored gives up much of them.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28315
PDF
-
From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution
2026-10-20 14:51:44Amit Lisha, Reut TsarfatyAbstract
Natural-language instructions often rely on high-level abstractions, such as asking an agent to ``stack blocks in a pyramid.'' Interpreting abstract instructions requires models to both identify the abstraction intended by the speaker, and unroll it into the many concrete actions that instantiate it. Language models struggle here: prior work has shown that performance degrades as the level of abstraction in the instruction rises. To bridge the gap between natural language abstraction and concrete actions, we propose to borrow from coding environments the notion of a {\em domain-specific language} (DSL), an explicit representation layer whose documented primitives name recurring abstractions that expand into concrete actions. We demonstrate the efficacy of DSLs for NL interpretation on \textsc{Hexagons}, a visually-grounded instruction-following task graded for abstraction. We further ask whether language models can induce such DSLs themselves from domain data. Our results show that while code generation consistently improves over direct inference, code generation over a human-curated DSL yields dramatic gains, up to 10 absolute F1 points, reaching the human skyline, with gains concentrated at {\em higher} abstraction levels. We confirm this pattern on the \textsc{Text2CAD} benchmark. At the same time, model-induced DSLs recover only part of this gain, remaining inconsistent across runs and short of their human-curated counterpart. Overall, the right representation closes much of the gap caused by high abstraction --- but inducing that layer of representation automatically is where models still fall short, and where we see a strong opportunity for the community to make progress.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28311
PDF
-
Reward Misspecification Degrades Chain-of-Thought Monitorability
2026-10-20 14:45:29Tianyi Lorena Yan, John HewittAbstract
Monitoring the chain-of-thought (CoT) of language models (LMs) is a key strategy for detecting and preventing misbehaviors for AI safety. As such, it is critical to identify reinforcement learning (RL) practices that lead to unmonitorable chain-of-thought. One such practice may be unavoidable: reward misspecification. As RL environments become more complex, it is infeasible to have perfect verification, and models are rewarded for behaviors that are different from the true task intent. We show that reward misspecification alone already degrades monitorability. We create a testbed with pairs of true reward aligned with task intent and misspecified rewards that favor a different behavior, so that reward hacking can be induced by training and labeled verifiably. Across three models and three tasks, CoT monitorability remains low as models' hack rates increase: the CoTs keep reasoning about the task intent while the outputs violate the intent and get rewarded. To mitigate unmonitorability without prior knowledge of the true reward or the hack, we collect rollouts with diverse rewards across training steps and use a LM to infer a reward description. We then inject the description into the input, which teaches the model to verbalize the reward. This reward description training improves monitorability by an average of 24% or 42% absolute, depending on the metric, across all models and tasks, and yields CoTs that reason about the misspecified reward explicitly. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28303
PDF
-
Adaptive Replay Refinement: Allocating Test-Time Compute Between Revision and Resampling
2026-10-20 14:41:46Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Ayesha Mohsin, Sarmad Bilal, Dean F. HougenAbstract
Test-time scaling allocates additional inference compute to refining existing solutions or generating new ones. This raises a fundamental question: Should I keep improving this solution, or stop working on it and try a completely new solution? Existing methods make this decision using fixed refinement schedules, self-verification judgments, or learned controllers, which can waste compute or rely on signals that may be incorrect or require additional training. We introduce Adaptive Replay Refinement (ARR), a training-free method that detects when a stationary revision reaches a fixed point and reallocates the released compute to a new independent sample; replay decoding treats the current solution as a draft and verifies unchanged tokens in parallel, enabling efficient fixed-point detection. Across seven models from five families and seven benchmarks, ARR matches majority voting on three of five mathematical reasoning benchmarks at equal compute, while reducing critical-path serial passes by up to 2.4 times. On MATH500, ARR achieves 84.6% accuracy with only 41% of the serial passes required by majority voting. These results demonstrate that detecting refinement exhaustion enables adaptive reallocation from revision to independent sampling, improving inference efficiency while highlighting the limits of self-revision. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28294
PDF
-
Forty Questions: Identifying a Language Model from One-Word Answers
Abstract
A model behind an API can be identified from its one-word answers to everyday questions such as "Name a sound" or "Name a poet". A model's profile records how often it gives each answer to each question. We attribute new answers to the model most likely to have given them. On a panel of 94 models, 40 answers identify the exact model 92.5% of the time, against 1.1% by chance. Profiles built through OpenRouter identified all ten models served by DeepInfra under blinded labels. A system prompt lowers accuracy by 6 to 16 points. We applied the method to 96 endpoints of 13 open models on OpenRouter, and 92 identify as the model they claim. Of the other four, one matches the claimed model with reasoning turned off. One serves Gemma 4 under the name Llama 4 Maverick: it names itself Gemma 4, and it is billed Gemma 4's token counts on every message. Two remain unresolved. Billing records also show context added to first-party models. Grok 4.7 is billed 1,247 input tokens for a one-line question that costs GPT-4o only 12 tokens, and five models state the current date without being billed for it. The questions come from a public census of model defaults, and the method costs cents per endpoint.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28281
PDF
-
MemT-1.0: Towards Memory-Native Evolution
2026-10-20 14:30:38Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Yu Yu, Zhichen Liu, Yuxiao Yi, Chunyu Li, Haoran Liu, Zhenkai Ding, Le Zhou, Juncheng Zhang, Boyu Chen, Zehao Lin, Guorui Li, Renyu Fu, Ji Li, Youyang Xia, Jiajun Shen, Harvey Li, Jingsong Zhou, Helan Hu, Tong Shen, Tianxiao Xu, Chenye Han, Weijie Li, Zhongquan Zhou, Hongming Xu, Yuekeng Li, Erenkai Zhu, Peng Yu, Wenhao Li, Jingyi Kang, Xixuan Hao, Xuzhou Zhu, Can Chen, Jiawei Liu, Chen Jiang, Tao Jiang, Fangwei Xiang, Zepeng Yao, Kai Chen, Guang Yang, Mingfei Lu, Chunhui Li, Zhengxuan Jiang, Bo Tang, Shiyu Zhan, Yihang Sun, Jie Chu, Wenjun Xiong, Zhenxiang Hua, Chen Lin, Detong Su, Dongyu Deng, Qiuping Ding, Guofeng Ding, Si Chen, Guohua Wen, Xu Chen, Zhi-Qin John Xu, Ying-Cong Chen, Ningyu Zhang, Haofen Wang, Muning Wen, Haotian Chen, Wentao Zhang, Xuanhe Zhou, Rita Zhang, Junchi Yan, Feiyu XiongAbstract
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano and MemT-1.0-Flash, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction in persistent storage relative to full context KV cache. By internalizing retrieved procedural experience, MemT-1.0 improves task success on agentic tasks, providing a practical step toward memory-native evolution.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26825
PDF
-
How Language Models Learn Taste: Brand Preference in LLMs
Abstract
Asked to name a running shoe brand, language models say Nike. Asked to recommend one, they say Brooks. This paper asks where models learn that taste. Across 102 models and 42 brand categories, the brand a model picks when recommending differs from the brand it names in 26. The field moves together to a shared recommendation. The Named brands are market leaders, and the Picked brands are mostly niche and specialist. Three open training pipelines show where this forms. Pretraining already attaches the recommended brand to advice. Supervised fine-tuning teaches the model to answer and mostly leaves the pick unchanged. Preference optimization (DPO) teaches the model which answer is better, and the pick moves in all three pipelines, by 11 to 24 points. The preference data contains almost no brands. DPO moves the model's judgments toward a second set of associations even when the preferred brand is not in the preference data, and the effect reaches beyond brands. Asked to choose a sauce, models switch from ketchup to pesto. We do not know exactly how these preferences arise. We suspect they come from the judge models that decide which answers count as better during preference training. For brands, a recommendation depends less on what a model knows about them than on whether they fit this taste.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28272
PDF
-
Can Language Models Get 'Aphasia' From Neuronal Ablation?
2026-10-20 13:49:25Pratik Worah, Randall BatemanAbstract
Progressive neuronal loss is the hallmark of neurodegenerative disease, yet how loss of neurons shapes the pattern of cognitive decline remains poorly understood. Here we systematically ablate neurons (computational units) in language models spanning recurrent long short-term memory (LSTM) and Transformer architectures and apply limited fine-tuning as a simple proxy for compensatory plasticity. With whole-unit ablation, LSTMs degrade gradually with syntactic and semantic faculties declining in parallel across mild-to-moderate damage. By contrast, Transformers exhibit late threshold-like collapse under feedforward multi-layer perceptron (MLP) ablation and smoother sigmoid-like decline under attention-head ablation. Qualitatively, MLP-ablated models continue to make within-category semantic substitutions (semantic paraphasias) alongside rising non-responses, paralleling Wernicke-type aphasia, while attention-head ablation produces a trend toward loss of semantic specificity similar to the semantic variant of primary progressive aphasia (svPPA). These findings indicate that feedforward and attentional pathways have functionally distinct failure modes, suggesting that architecture-dependent failure profiles may offer new computational perspectives on aphasic syndromes and neurodegenerative diseases as an in silico model. Notably, early accuracy retention under Transformer attention-head ablation qualitatively parallels pre-symptomatic reserve before the 40--60% neuronal loss reported by Gomez-Isla et al. (1996) when clinical symptoms emerge in Alzheimer's disease, whereas the steadier LSTM decline parallels the symptomatic progression described by DeKosky and Scheff (1990) and Terry et al. (1991).
Abstract (translated)
URL
https://arxiv.org/abs/2610.28214
PDF
-
Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons
2026-10-20 13:27:40Tzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin, Hao Tang, Hung-yi LeeAbstract
While the language model backbone is pretrained on text alone, large audio-language models (LALMs) can, to a great extent, recognize acoustic attributes, such as emotion, speaker gender, and spoken language. However, it is unclear how the audio representation is integrated, if at all, with the other text representation before the model produces text. We hypothesize that there is a shared subspace where the audio and text representations are aligned. To test this hypothesis, we identify cross-modal neurons that are responsible for representing both audio and text. We find alignment between audio and text neurons to various degrees across three LALMs and four acoustic attribute types. Causal interventions, steering and deactivating the neurons, confirm that the cross-modal neurons are not just necessary for prediction but can also be manipulated.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28189
PDF
-
Occupational Uniqueness and Wage Growth
Abstract
Changes in occupational task content may have different economic implications depending on whether the tasks gained or lost are occupation-specific or already widespread across the economy. Existing measures of occupational task change largely abstract from this distinction, treating occupations as self-contained task bundles rather than accounting for how tasks are distributed across occupations. We develop a framework to measure a distinct dimension of occupational change, one that goes beyond task expertise or task content: task structure. Using this new framework that tracks tasks across occupations and over time, we separate changes in task quantity from changes in occupational uniqueness, defined as the distinctiveness of an occupation's task bundle relative to other occupations. Using a harmonized dataset of 196563 task statements from the Dictionary of Occupational Titles and O*NET spanning 1977-2018, we measure task diffusion, occupational uniqueness, and distinct dimensions of task addition and removal. Occupations that become less unique are also associated with lower wage growth, and the wage associations of task additions and removals depend on how widely the affected tasks are performed elsewhere. Adding highly diffused tasks is associated with lower wage growth, as is removing occupation-specific tasks. At the economy-wide dimension, however, the pattern differs: the addition of new tasks is positively associated with wage growth, whereas the removal of tasks is negatively associated with it. Taken together, these results show that similar changes in the number of tasks performed by an occupation can reflect economically distinct processes. Incorporating the cross-occupational distribution of tasks, therefore, provides a richer account of occupational change and its relationship to the wage structure.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28133
PDF
-
Reading Too Much Into It? Interpretive Preferences and Commitment in LLM Mentalisation under Ambiguity
2026-10-20 12:18:11Stephanie Fong, Yiwen Jiang, Qingyang Xu, Zimu Wang, Yaling Shen, Xiangyu Zhao, Jiahe Liu, Yinghao Zhang, Vincent Lee, Dominic DwyerAbstract
Large Language Models (LLMs) are increasingly used for interpersonal advice, potentially shaping how users interpret ambiguous social encounters. Existing Theory of Mind evaluations typically rely on predefined answers, while uncertainty research overlooks LLMs' preferred explanations and confidence under psychological distress. To address these gaps, we introduce MentalLoom, a novel evaluation of LLM mentalisation comprising 604 ambiguous social episodes, matched depression and social anxiety disclosures, and four-turn dialogues with unchanged event evidence. Across eight LLMs, disclosures initially elicited more negative explanations overall but more positive narrator-directed interpretations. Scripted repeated questioning showed greater emotional support, stronger positive narrator-directed endorsement, and higher certainty without new event evidence. These findings show that user context can reshape interpretive preferences and commitment while the underlying ambiguity remains unresolved.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28105
PDF
-
Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts
2026-10-20 11:50:25Devansh Srivastav, David Pape, Samira Abedini, Lea Sch\"onherrAbstract
LLMs increasingly operate over mixed-sensitivity contexts, where they must reason over information ranging from public to confidential while disclosing only what the user is authorised to receive. Existing approaches enforce access control as a binary decision: either fully answering or refusing, without regulating how much or what kind of information is revealed if access is granted, leading to over-refusal or unintended leakage. We introduce graduated disclosure, an access-control formulation in which the level of detail and sensitivity in a model's response is calibrated to the user's authorisation rather than treated as a grant-or-deny decision. We model graduated disclosure as a disclosure-aware generation problem and propose a reward-based optimisation framework that shapes responses toward level-appropriate abstractions while penalising unauthorised factual leakage, including paraphrases and approximations. We evaluate our approach on enterprise and clinical benchmarks and compare it with prompt-based, gating, and supervised baselines. Experiments show that our method substantially reduces information leakage while preserving correctness and utility. These results suggest that disclosure control must be integrated into the generation process itself to enable secure yet useful LLM deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28067
PDF
-
Poisoning-Based Backdoors Are Not Cryptographic
Abstract
To defend against backdoor attacks on neural networks, the defender must identify the verifier function that determines whether an input is a trigger, rather than rejecting individual triggers in isolation, since an attacker can generate new triggers satisfying the same verifier faster than they can be blocked. If a backdoor verifier could be installed with the asymmetry of a cryptographic authentication scheme, in which only the attacker can produce trigger inputs while the defender cannot reverse-engineer the verifier from observations, learning-based defense would be impossible in principle. We show that no such asymmetry can arise from poisoning-based installation, in which the only verifier-dependent input to training is a poisoned dataset. The argument is a reduction. A training procedure that installs a verifier from poisoned data, so that the backdoor fires on unseen triggers while benign behavior is preserved, is itself a learner for that verifier. Any verifier that is computationally hard to learn is therefore impossible to install through poisoning, and any verifier that poisoning can install is reconstructible by a white-box defender holding comparably many labeled trigger observations. A complementary argument shows that a secret key supplied to the model at inference is observable to the same defender. The result takes representative trigger observations as given and concerns when the backdoor fires rather than what it does. Experiments on instruction-tuned large language models confirm the dichotomy, with no configuration yielding a backdoor that is both effective for the attacker and irrecoverable for the defender.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28045
PDF
