SwissGov-RSD is the first naturalistic cross-lingual document-level benchmark with human token-level semantic difference annotations, on which both LLMs and encoders show a large performance gap relative to simpler settings.
super hub Mixed citations
write newline
Mixed citation behavior. Most common role is background (50%).
192
Pith papers citing it
Background
50% of classified citations
hub tools
citation-role summary
background 9
other 5
method 2
citation-polarity summary
claims ledger
- background Flesch-Kincaid Grade Level 8.97 9.08 -0.11 -0.1673 -0.1528 Table 5: Textual complexity metrics and their correlation with frequency. Corr. denotes correlation. We use nlp = spacy.load("en_core_web_sm") for calculation. Bin Range N BLEU(HF) BLEU(LF)∆BLEU(HF-LF) chrF(HF) chrF(LF)∆chrF(HF-LF) Strict Depth Match 144 20.82 16.04 +4.78 48.73 43.86 +4.87 [0%,5%) 144 20.82 16.04 +4.78 48.73 43.86 +4.87 [5%,10%) 6 22.45 14.79 +7.65 49.76 49.19 +0.57 [10%,15%) 71 19.12 15.38 +3.74 46.19 44.71 +1.47 [15%,2
authors
co-cited works
representative citing papers
BEAVER is the first text-to-SQL benchmark from private enterprise data warehouses, revealing SOTA agentic frameworks achieve only 10.8% accuracy on complex real-world queries.
A rule-generation perspective lets LLMs write programs as rules for data mapping and applies complexity theory to estimate their compositionality, tested on string-to-grid tasks.
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
Cross-cultural survey of 4,641 participants shows LLM emotional support adoption varies widely by country and demographics, with socioeconomic status as strongest predictor of trust and use, and English-speaking nations more accepting than others in Europe.
VLMs reach only 42.1% exact accuracy on counting pushups in videos, with weaker models exploiting modal counts, and 1k-sample fine-tuning transfers gains to MVBench, PerceptionTest, and TVBench.
A controlled formal language task reveals fine-tuning outperforms in-context learning on in-distribution generalization but equals it on out-of-distribution, with ICL showing greater sensitivity to model size and tokenization.
StoryTR is a new benchmark and agentic data pipeline that adds explicit Theory of Mind reasoning chains to train smaller video retrieval models, yielding a 15% relative IoU gain over larger baselines on narrative content.
Language models frequently violate temporal scope stability in multi-turn dialogues by drifting toward present-day assumptions even when they possess the correct facts.
BERAG applies Bayesian ensemble weighting of individual documents via token-by-token posterior updates in retrieval-augmented generation, yielding gains on knowledge-based visual QA tasks.
Subword tokenization impairs phonological knowledge encoding in LMs, but an IPA-based fine-tuning method restores it with minimal impact on other capabilities.
BiasedTales-ML provides a parallel multilingual corpus of LLM-generated children's stories that reveals substantial cross-lingual differences in narrative attributes not captured by English-centric analyses.
Conjunctive prompt attacks split adversarial elements across agents and routing paths in multi-agent LLM systems, evading isolated defenses and succeeding through topology-aware optimization.
VisPCO uses continuous relaxation, straight-through estimators, and budget-aware Pareto-frontier learning to automatically discover optimal visual token pruning configurations that approximate grid-search results across VLMs and benchmarks.
HintPilot synthesizes semantics-preserving compiler hints via retrieval-augmented LLM generation and profiling-guided refinement, delivering up to 6.88x geometric mean speedup over -Ofast on PolyBench and HumanEval-CPP while preserving correctness.
R²A uses a hybrid ensemble surrogate router and suffix optimization to significantly increase black-box LLM router selection of expensive models across query distributions.
ADAPT augments planners with affordance reasoning to raise task success in environments with unspecified and time-varying object affordances, and a LoRA-finetuned VLM backend beats GPT-4o on the new DynAfford benchmark.
Schema-key wording functions as an implicit instruction channel under constrained decoding, with experiments showing that rephrasing only the keys can substantially change accuracy on math benchmarks while prompt, model, structure, and decoding remain unchanged.
SPAGBias reveals that LLMs form nuanced gender associations with specific urban micro-spaces that exceed real-world distributions and produce failures in planning and descriptive tasks.
CAR is a new retrieval objective that targets the currently active authority set rather than most-similar documents, with theorems on coverage conditions and evaluations showing two-stage methods outperform dense retrieval on authority-governed datasets.
Multimodal ICL lags text-only ICL in few-shot settings due to weak cross-modal reasoning alignment and unreliable task mapping transfer, with an inference-stage method proposed to strengthen transfer.
Reinforcement learning with a multi-part reward teaches LLMs to output independent, meaning-preserving sentence edits that raise argument appropriateness close to full rewriting.
Tabular QA LLMs are overconfident, but Multi-Format Agreement using Markdown/HTML/JSON/CSV variants improves AUROC to 0.80 and cuts calibration error by 44-63% at lower cost than sampling.
EgoEsportsQA is a new egocentric video QA benchmark from esports matches that shows state-of-the-art Video-LLMs reach only 71.58% accuracy and struggle more with tactical reasoning than basic perception.
citing papers explorer
-
SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents
SwissGov-RSD is the first naturalistic cross-lingual document-level benchmark with human token-level semantic difference annotations, on which both LLMs and encoders show a large performance gap relative to simpler settings.
-
Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models
Spoken language models exhibit style amnesia and fail to maintain instructed paralinguistic styles across multi-turn conversations, with explicit recall offering partial mitigation.
-
CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics
CricBench is the first multilingual Text-to-SQL benchmark for cricket analytics, showing LLMs achieve over 98% execution accuracy but under 29% semantic correctness with a 37-55 point gap versus general benchmarks like BIRD.
-
MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
MURPHY improves code generation pass rates by up to 6% through retrospective credit assignment on multi-turn feedback trees using max or mean reward propagation.
-
TSVer: A Benchmark for Fact Verification Against Time-Series Evidence
TSVer is a new benchmark dataset for fact verification against time-series evidence, with 304 annotated real-world claims, 400 time series, verdicts, and justifications, plus baseline results showing current models struggle.
-
AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models
AudioRole provides 1M+ character-grounded audio-text dialogues from TV series plus ARP-Eval to train and measure audio role-playing models, with ARP-Model showing 0.31 acoustic and 0.36 content personalization scores.
-
SiDiaC: Sinhala Diachronic Corpus
SiDiaC is a new historical corpus of Sinhala literary works spanning the 5th to 20th centuries, constructed via OCR digitization, orthography modernization, and genre-based annotation.
-
V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
V-SEAM combines concept-level visual semantic editing with attention head modulation to identify positive and negative contributors across object, attribute, and relationship levels, then uses this to improve VLM performance on VQA benchmarks.
-
Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
Evaluations of 53 LLMs on 14 basic math tasks show reasoning models use ~18x more tokens with sometimes lower accuracy, non-monotonic gains from extended budgets, and sharp performance drops under token constraints.
-
ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
ExaGPT uses span-level similarity retrieval from human and LLM datastores to detect machine-generated text while supplying the matching spans as human-interpretable evidence, achieving up to 37-point accuracy gains over prior interpretable detectors at 1% FPR.
-
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
FastKV decouples prefill context reduction via Token-Selective Propagation from independent KV cache selection, delivering up to 1.82x prefill and 2.87x decoding speedups while matching decoding-only accuracy.
-
SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation
SpidR-Adapt uses meta-learning with a first-order bi-level optimization heuristic to adapt speech representations to new languages with less than 1 hour of data, achieving 100x better efficiency than standard training.
-
Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection
FinFRE-RAG combines importance-guided feature reduction with label-aware retrieval-augmented generation to boost LLM performance on tabular fraud detection across four public datasets while providing human-readable rationales.
-
Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation
Progress Ratio Embeddings use a trigonometric progress-ratio signal to deliver stable length control in transformers that generalizes to unseen target lengths.
-
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Entropy Ratio Clipping introduces a global entropy-ratio constraint that stabilizes RL policy updates in LLM post-training beyond local PPO clipping.
-
CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents
CodeDistiller distills 250 materials-science GitHub repositories into vetted code libraries that improve the accuracy and scientific soundness of experiments generated by ASD agents.
-
PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
PEFT-Bench is a standardized end-to-end benchmark for 7 PEFT methods across 27 NLP datasets on autoregressive LLMs, accompanied by the PSCP metric that penalizes based on trainable parameters, inference speed, and training memory.
-
Stress Testing Factual Consistency Metrics for Long-Document Summarization
Short-form factual consistency metrics produce inconsistent scores on semantically equivalent long-document summaries and lose reliability on information-dense claims.
-
ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
ReFACT benchmark reveals LLMs show a persistent salient distractor failure mode where 61% of incorrect error span predictions are semantically unrelated to actual errors, persisting across model sizes, and comparative judgment yields lower F1 than independent detection.
-
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
CE-GPPO preserves bounded gradients from clipped tokens in PPO to regulate entropy evolution and improve performance on mathematical reasoning benchmarks.
-
MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification
MOSAIC achieves mean macro F1 of 88 on chest X-ray report classification across five datasets in four languages using a 4B-parameter open model with low GPU memory and few-shot or light fine-tuning options.
-
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
ReGATE introduces a teacher-student adaptive token elision method that reduces training tokens to 38% while matching or exceeding baseline accuracy on multimodal benchmarks.
-
SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding
SessionIntentBench is a large-scale multimodal benchmark for inter-session intention-shift modeling in e-commerce, with 1.95M intention entries and human-annotated gold labels showing current L(V)LMs struggle but improve when intention is injected.
-
SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models
SLoW selects low-frequency word dictionaries to boost LLM translation quality and efficiency across 100 languages from FLORES.
-
Synthia: Scalable Grounded Persona Generation from Social Media Data
Synthia creates scalable personas from Bluesky posts that better match human survey responses than prior methods, uses smaller models, and retains social network structure for network-aware analysis.
-
PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation
PromptSuite is a modular, extensible, task-agnostic framework for automatically generating diverse prompt variations to support robust multi-prompt LLM evaluation.
-
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models
The work identifies a small set of attention heads in VLMs that mediate conflicts between parametric knowledge and visual input, and shows that intervening on them steers model behavior while attention patterns provide precise image-region attribution.
-
WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis
WiseMind is a dual-agent LLM system with DSM-5 knowledge graph guidance that reaches 85.6% top-1 diagnostic accuracy on simulated and real psychiatric conversations while producing supportive responses.
-
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
-
MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation
MapNav uses annotated semantic maps as memory for VLN agents, claiming SOTA results in simulation and real-world tests while promising code and data release.
-
CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models
Introduces CounterBench benchmark and CoIn iterative reasoning method showing LLMs perform near random on formal counterfactual tasks but improve substantially with guided backtracking.
-
MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms
Frontier LLMs achieve only moderate performance on multi-file unit test generation, with basic executability and cascade errors common, but manual and self-error-fixing mechanisms yield measurable gains.
-
The Differences Between Direct Alignment Algorithms are a Blur
A controlled unification of direct alignment algorithms shows the ranking objective (pairwise vs pointwise) drives alignment quality more than the scalar score optimized.
-
A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification
Lasso-selected speech tokens enhance text LLMs for multimodal classification by reducing long audio sequences to task-relevant features via self-supervised adaptation.
-
Different types of syntactic agreement recruit the same units within large language models
Different types of syntactic agreement recruit overlapping units within LLMs, indicating that agreement forms a meaningful functional category across English, Russian, Chinese, and structurally similar languages.
-
PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.
-
ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction
ZoFia is a zero-shot fake news detection framework that uses hierarchical entity salience retrieval followed by multi-LLM adversarial debate to improve robustness over single-model approaches.
-
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
LLM-enhanced multi-view gated attention MIL framework using ELB decomposition improves cognitive distortion classification on Korean and English therapy datasets.
-
Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
Controlled prompt interventions reveal strong affiliation bias in LLM peer reviews favoring top-ranked institutions, plus effects from seniority and publication history.
-
Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
A framework for inference-time knowledge graph construction and expansion improves factual accuracy in LLMs on three QA benchmarks by combining internal LLM knowledge with selective external retrieval.
-
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
Censored LLMs achieve 69.0% strict accuracy in hate speech detection versus 64.1% for uncensored models and resist persona-based ideological influence better, but all exhibit overconfidence, irony failures, and group fairness disparities.
-
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
SMCS coordinates 15 open-source LLMs via retrieval-based prior selection and exploration-exploitation posterior enhancement, outperforming GPT-4.1 by 5.36% and GPT-o3-mini by 5.28% on eight benchmarks.
-
Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
Language composition in training data creates opposing effects on CLIR and mono-IR performance for Korean-English retrieval, which model merging can partially resolve.
-
From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction
8:16 sparsity with variance correction and outlier handling lets compressed LLMs match or exceed dense-model accuracy under fixed memory limits, outperforming the common 2:4 pattern in flexibility.
-
MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis
MSMO framework achieves claimed SOTA cross-lingual ABSA via sentence- and aspect-level alignment, code-switching, consistency training, and knowledge distillation.
-
FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints
FediLoRA is a lightweight federated LoRA aggregation method that jointly mitigates missing modalities and heterogeneous ranks in collaborative fine-tuning of foundation models.
-
Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?
LLM accuracy on reasoning tasks differs significantly by question type, with step-by-step reasoning accuracy often uncorrelated to final answer selection.
-
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan
A 72GB Tibetan corpus enables continual pre-training of Qwen2.5-7B and a 50B-A10B MoE model, with new benchmarks showing outperformance over prior Tibetan models.
-
EduCoder: An Open-Source Annotation System for Education Transcript Data
EduCoder supplies a collaborative annotation platform specialized for education transcripts that supports complex codebook definition, mixed annotation types, contextual materials, and inter-annotator comparison.
- MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)