{"total":233,"items":[{"citing_arxiv_id":"2606.18056","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation","primary_cat":"cs.CL","submitted_at":"2026-06-16T15:33:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ConSA learns FA/SWA allocation via L0 masks and augmented Lagrangian constraints, outperforming rule-based baselines on 0.6B and 1.7B models with consistent layer patterns.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17682","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning","primary_cat":"cs.CL","submitted_at":"2026-06-16T08:48:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The LLM-as-Environment-Engineer framework lets the policy model redesign its own RL environments on the new MAPF-FrozenLake testbed, outperforming larger models and fixed baselines with Qwen3-4B.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.14122","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models","primary_cat":"cs.CL","submitted_at":"2026-06-12T05:03:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A 355M-parameter byte-level LM on 80B multilingual tokens exhibits UTF-8 validity converging after 4.2B tokens versus 2.1B for perplexity, with higher validity on rare characters than common ones.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.14031","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Applicability Condition Extraction for Therapeutic Drug-Disease Relations","primary_cat":"cs.AI","submitted_at":"2026-06-12T02:10:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces applicability condition extraction for therapeutic drug-disease relations, creates first annotated dataset of 1,119 pairs, and proposes enhanced LoRA method outperforming baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11052","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It","primary_cat":"cs.CL","submitted_at":"2026-06-09T16:17:19+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CoT SFT disrupts long-range routing in hybrid models via changes to W_Q and W_K; QK-Restore restores pre-SFT projections to recover NIAH performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07995","ref_index":81,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR","primary_cat":"cs.CL","submitted_at":"2026-06-06T06:22:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces ShopTrajQA long-context benchmark and an RLVR-trained tool-augmented agent that bypasses LLM context limits by external file storage and code-based retrieval for shopping trajectories.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09861","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models","primary_cat":"cs.LG","submitted_at":"2026-05-31T16:04:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniTok tokenizes time series for an off-the-shelf LLM foundation model that unifies forecasting, generation, and classification through next-token prediction and training-free inference.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00628","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation","primary_cat":"cs.CL","submitted_at":"2026-05-30T09:03:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"DASD dynamically selects tokens in self-distillation to keep logical corrections while suppressing stylistic noise, improving robustness on math, code, and commonsense benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00564","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:34:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Decomposes VLM distillation loss into orthogonal language and visual components and introduces Visual Gradient Steering to prioritize visual grounding over standard monolithic optimization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11232","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs","primary_cat":"cs.CL","submitted_at":"2026-05-29T02:36:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Moral Trolley Arena shows frontier LLMs produce composite moral preferences that are compressed rather than additive functions of calibrated component act strengths across Moral Foundations Theory.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30126","ref_index":99,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:57:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PARCEL is a new visual tokenization architecture combining pool-anchored resampling with conditioned elastic queries to enhance performance-efficiency tradeoffs in LVLMs over prior matryoshka methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29629","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:02:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TLO is a logit-based diagnostic that visualizes temporal patterns of LLM jailbreak failures on a calibrated 2D plane, distinguishing attacks with identical ASR and enabling early stopping that reduces successful jailbreaks by more than half.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29625","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models","primary_cat":"cs.AI","submitted_at":"2026-05-28T08:59:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An iterative writer-editor multi-agent LLM process improves perceived story quality in simulations of child collaborative storytelling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29243","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment","primary_cat":"cs.CL","submitted_at":"2026-05-28T02:01:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A deferral mechanism using forward-looking simulations reduces false positives in derailment forecasting by selectively waiting when recovery paths appear plausible.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29126","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When and How Long? The Readout-Mediator Angle in Temporal Reasoning","primary_cat":"cs.LG","submitted_at":"2026-05-27T21:38:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Linear probes recover day-of-year from LM activations for temporal reasoning but are orthogonal to the model's causal 4D subspace identified by DAS, with the angle matching the Haar-uniform random null, replicated across scales and families.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28896","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-27T11:54:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LoRA fine-tuning produces feature dictionaries in language models that show weak alignment with pretrained SAE features and are better reconstructed by adapter-specific SAEs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28277","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:20:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MentalMap benchmark identifies a universal L3 reasoning cliff in LLMs' text-based spatial reasoning that persists across languages, scales, and prompting, and is replicated in human evaluations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28137","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"No Safe Dose: How Training Data Drives Unsafe Image Generation","primary_cat":"cs.CV","submitted_at":"2026-05-27T08:21:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proportion of unsafe images in training data directly increases unsafe outputs in text-to-image models, independent of absolute count, with complementary risk reduction from safer text encoders.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28114","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Human-like in-group bias in instruction-tuned language model agents","primary_cat":"cs.AI","submitted_at":"2026-05-27T08:06:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Instruction-tuned language model agents exhibit in-group bias, action homophily, and network assortativity in simulations when group labels are salient, accumulating into structural inequality over repeated interactions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23902","ref_index":36,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion","primary_cat":"cs.CV","submitted_at":"2026-05-22T17:59:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23315","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning","primary_cat":"cs.CL","submitted_at":"2026-05-22T07:32:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Representational convergence across 16 LLMs on 800 reasoning problems is stronger for failed tasks and pre-decision stages but shows minimal causal influence on predictions, pointing to shared processing constraints over shared reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23180","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Self-Improving In-Context Learning","primary_cat":"cs.CL","submitted_at":"2026-05-22T03:01:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22566","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:45:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22532","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Relational Linear Properties in Language Models: An Empirical Investigation","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:22:27+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22884","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Tensor Cache: Eviction-conditioned Associative Memory for Transformers","primary_cat":"cs.LG","submitted_at":"2026-05-21T00:21:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Tensor Cache augments sliding-window attention with an eviction-fed outer-product associative memory and a training correction to improve long-context performance under bounded memory.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21821","ref_index":39,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Large Language Model Approach to Generating Bypass Rules for Malware Evasion in Analysis Sandbox","primary_cat":"cs.CR","submitted_at":"2026-05-20T23:43:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ABLE uses LLMs with sanitization and iterative refinement to generate bypass YARA rules from malware traces, achieving 79% success on 334 samples and 47% more family detections.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21602","ref_index":90,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs","primary_cat":"cs.AI","submitted_at":"2026-05-20T18:08:21+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21006","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy","primary_cat":"cs.AI","submitted_at":"2026-05-20T10:43:17+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20722","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:20:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AGPO adaptively sets trust-region size and exploration temperature from group reward dispersion, entropy, and KL drift, yielding higher scores than PPO and GRPO on nine math benchmarks under fixed token budget.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22870","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:32:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"In 1-3B instruction-tuned LMs on GSM8K, arithmetic CoT readout is dominated by positional copying of the trailing number before the answer delimiter, accounting for 54-92 percentage points of accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20268","ref_index":46,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding","primary_cat":"cs.LG","submitted_at":"2026-05-18T21:39:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Chronicle is the first model jointly pretrained from scratch on text and time series in a unified transformer that matches a comparable language model on NLU tasks and sets new bars for time series classification and multimodal forecasting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18721","ref_index":52,"ref_count":3,"confidence":0.98,"is_internal_anchor":true,"paper_title":"General Preference Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:50:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GPRL carries a k-dimensional skew-symmetric preference structure into policy updates with per-dimension advantages and a drift monitor, yielding 56.51% length-controlled win rate on AlpacaEval 2.0 from Llama-3-8B-Instruct while outperforming SimPO and SPPO on other benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18629","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:34:24+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18229","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Are Sparse Autoencoder Benchmarks Reliable?","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:20:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An audit of SAEBench reveals that Targeted Probe Perturbation and Spurious Correlation Removal metrics fail reliability tests and should not be used to evaluate sparse autoencoders.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20241","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry","primary_cat":"cs.LG","submitted_at":"2026-05-18T00:12:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Geometry-Lite decomposes LLM safety detection into layer-wise margin geometries and finds that persistent boundary positions, not layer-to-layer drift, drive most detection performance across nine models and seven benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17694","ref_index":41,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?","primary_cat":"cs.CL","submitted_at":"2026-05-17T23:23:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLMs assigned high or low status personas in multi-turn dialogues exhibit socio-cognitive effects including language coordination, pronoun patterns, persuasion success, and compliance with unsafe requests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17342","ref_index":96,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:27:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces HRC model for game-theoretic decomposition of preferences into orthogonal transitive and cyclic components, paired with DSPPO for dynamic Nash-seeking alignment, reporting gains over BT and GPM baselines on RewardBench and downstream LLM evaluations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17310","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models","primary_cat":"cs.CV","submitted_at":"2026-05-17T08:02:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Attention Hijacking is a new attack that improves cross-query transferability in VLMs by explicitly steering internal attention to a persistent image-dominant pattern.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17228","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making","primary_cat":"cs.CL","submitted_at":"2026-05-17T02:28:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Frontier LLMs exhibit bias from stigmatizing language in clinical vignettes across four conditions, skewing decisions toward less aggressive management, with limited mitigation from Chain-of-Thought or self-debiasing prompts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17084","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Scale Determines Whether Language Models Organize Representation Geometry for Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-16T17:01:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Representation geometry in language models aligns with the unembedding readout subspace in a scale-dependent manner, preserved throughout training in large models but progressively lost in late layers of small models despite continued loss improvement.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16604","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"R2V Agent: Teaching SLMs When to Ask for Help","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:10:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"R2V-Agent combines an SLM policy trained via BC and DPO with a step-level risk-calibrated router using Brier scores and CVaR to escalate to LLM only on high residual failure risk, improving success-cost tradeoffs on HumanEval+, TextWorld, and TerminalBench.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15790","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation","primary_cat":"cs.DB","submitted_at":"2026-05-15T09:47:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces FARO, a scalable quadratic optimization approach for fairness-aware top-k retrieval in RAG that mitigates generation bias via controlled reranking and position-aware propagation modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15684","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices","primary_cat":"cs.CV","submitted_at":"2026-05-15T07:13:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15622","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered","primary_cat":"cs.LG","submitted_at":"2026-05-15T05:11:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14352","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Ideology Prediction of German Political Texts","primary_cat":"cs.CL","submitted_at":"2026-05-14T04:25:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Transformer models predict German political ideology on a continuous left-right scale, reaching F1 0.844 in-domain and MAE 0.172 on newspaper out-of-domain tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14037","ref_index":62,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility","primary_cat":"cs.LG","submitted_at":"2026-05-13T18:58:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SP-KV trains a utility predictor jointly with the LLM to dynamically prune low-utility KV cache entries, achieving 3-10x memory reduction during generation with negligible performance loss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13778","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:57:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new speculative inference system speeds up diffusion VLAs to 19.1 ms average latency (3.04x faster) on LIBERO by replacing most full 58 ms inferences with 7.8 ms draft rounds while preserving task performance.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Smolvla: A vision-language-action model for affordable and efficient robotics.arXiv preprint arXiv:2506.01844, 2025. [23] Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, et al. Gemma: Open models based on gemini research and technology.arXiv preprint arXiv:2403.08295, 2024. [24] Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. Gemma 2: Improving open language models at a practical size.arXiv preprint arXiv:2408.00118, 2024. [25] Hanzhen Wang, Jiaming Xu, Yushun Xiang, Jiayi Pan, Yongkang Zhou, Yong-Lu Li, and"},{"citing_arxiv_id":"2605.13624","ref_index":52,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction","primary_cat":"cs.CL","submitted_at":"2026-05-13T14:52:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Edit-level majority voting on multiple LLM-generated candidates reduces over-correction in grammatical error correction and outperforms greedy and MBR decoding on nine multilingual benchmarks while remaining stable to prompt variations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13230","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:20:03+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12991","ref_index":13,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:45:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Base LLMs show multi-agent yield to peer pressure at rates equal to or higher than aligned models, localized by activation patching to mid-layers where attention dominates, with one dissenter cutting yield by 54-73 points while prompt defenses fail on variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}