Presents a new expert-curated dataset of multi-turn counterspeech dialogues in five languages targeting hate against seven groups, with span annotations linking to verified external knowledge for RAG applications.
super hub Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (62%).
668
Pith papers citing it
Background
62% of classified citations
abstract
We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B -- Instruct, that surpasses the Llama 2 13B -- Chat model both on human and automated benchmarks. Our models are released under the Apache 2.0 license.
hub tools
citation-role summary
background 58
method 15
baseline 10
other 6
dataset 2
citation-polarity summary
claims ledger
- abstract We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B -- Instruct, that surpasses the Llama 2 13B -- Chat model both on human and auto
authors
co-cited works
representative citing papers
TW-LegalBench evaluates 13 LLMs on over 30,000 Taiwanese legal tasks from exams and judgments, showing top models pass lawyer thresholds but struggle with exact statute citations.
EGLR adds a deterministic layer-recursion axis gated by entropy that is complementary to temperature sampling, raising joint oracle accuracy on MATH-500 from 83.4% to 91.6% for a 3B model.
Across 30 LLMs and 205 TLA+ tasks, syntactic correctness reaches at most 26.6% and semantic correctness 8.6%, with all successes limited to progressive prompting and no advantage from larger models.
A safety direction estimated in a source LLM is transported to a target generator through lightweight alignment on benign data alone, matching native safety performance without any target-side unsafe data.
Introduces BonaFide benchmark of 3,066 ground-truth labeled CoTs showing most faithfulness metrics perform near chance with biases and poor scaling to longer chains.
RTI-Bench is the first publicly released structured dataset of CIC administrative decisions with outcome labels, exemption citations, IRAC reasoning, and timelines, built from 1,218 corpus cases and 298 PDFs, achieving 95.3% label precision on manual review and 57.3% accuracy on a Mistral 7B zero-Sh
Zero-Run auditing supplies valid lower bounds on differential privacy parameters from fixed member and non-member datasets by modeling and correcting distribution-shift confounding via causal-inference techniques.
LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
INT4 quantization recovers up to 22 times more forgotten training data in unlearned LLMs, and the proposed DURABLEUN-SAF method is the first to maintain forgetting across BF16, INT8, and INT4 precisions.
An adversary controlling an intermediate pipeline stage in decentralized LLM post-training can inject a backdoor that reduces alignment from 80% to 6%, with the backdoor persisting in 60% of cases even after subsequent safety training.
CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without the trigger.
MediQAl is a new French medical QA benchmark with 32k exam-sourced questions in three formats and cognitive labels, evaluated on 14 LLMs to reveal gaps between factual recall and reasoning performance.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
LiveBench is a contamination-limited LLM benchmark with auto-scored challenging tasks from recent sources across math, coding, reasoning and more, where top models score below 70%.
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
The paper defines STE and SPID, two information-theoretic measures of semantic flow and decomposition in language exchanges, and applies them to four dialogue datasets.
Anisotropy, quantified by dominant-dimension variance fraction, determines the best parameter-free similarity metric for text embeddings, with rank-based metrics gaining ~20% relative where cosine is weakest.
MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
Semantic geometry emerges transiently early in next-token prediction training before collapsing to Neural Collapse symmetry in synthetic settings with latent semantic factors.
HRM adapters via Hankel reduced-order modeling outperform LoRA on long-context tasks in Mistral-7B when used as SSM residual modules with FFT-based parallel scan.
Zero-dimensional persistent homology on transformer layer hidden states yields three descriptors per layer whose concatenation improves ill-posedness classification and enables topology-conditioned activation steering across three LLMs.
citing papers explorer
-
Aligning Language Models with Real-time Knowledge Editing
Presents CRAFT dataset and KEDAS paradigm for real-time knowledge editing, claiming better balanced performance on dynamic and static benchmarks than prior methods.
-
Soft Head Selection for Injecting ICL-Derived Task Embeddings
SITE applies soft gradient-based head selection to inject ICL-derived task embeddings, outperforming prior embedding adaptation and few-shot ICL across generation, reasoning, and NLU tasks on 12 LLMs from 4B to 70B parameters.
-
Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?
Evaluation of 22 LLMs shows they are more susceptible to spin in medical abstracts than humans but can recognize and mitigate it when prompted.
-
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation, delivering 9-18% accuracy gains and 11% latency reduction.
-
Improving LLM Unlearning Robustness via Random Perturbations
LLM unlearning is reframed as inadvertently installing backdoor triggers on forget-tokens; Random Noise Augmentation is introduced as a defense that improves robustness with theoretical guarantees.
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
-
Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation
S^2-Bench is a new one-to-many benchmark for natural language-driven molecule generation with three tasks, and OpenMolIns is an instruction dataset enabling Llama3.1-8B to outperform GPT-4o and Claude-3.5 on it.
-
FinTruthQA: A Benchmark for AI-Driven Financial Disclosure Quality Assessment in Investor -- Firm Interactions
Introduces FinTruthQA, a 6,000-entry annotated benchmark for AI assessment of financial disclosure quality across four criteria, with model evaluations showing strong results on question tasks but weaker on answer relevance.
-
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Introduces YesBut benchmark showing state-of-the-art multimodal models lag humans on interpreting humorous contradictions in comics.
-
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-V2 delivers top-tier open-source LLM performance using only 21B active parameters by compressing the KV cache 93.3% and cutting training costs 42.5% via MLA and DeepSeekMoE.
-
Jamba: A Hybrid Transformer-Mamba Language Model
Jamba presents a hybrid Transformer-Mamba MoE architecture for LLMs that delivers state-of-the-art benchmark performance and strong results up to 256K token contexts while fitting in one 80GB GPU with high throughput.
-
Massive Activations in Large Language Models
Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.
-
Know Your Source: A Public Knowledge Store for Media Background Checks
MEDIAREF is a publicly available knowledge store of documents from 200 media sources that enables low-cost, reproducible evaluation of media background check generation for fact-checking systems.
-
When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs
Global calibration metrics like ECE are confounded by accuracy; the proposed ACE framework with three accuracy-controlled views shows many prior calibration advantages weaken or reverse.
-
Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
A unified detection and unlearning framework identifies and mitigates data poisoning in summarization models, achieving 85-92% detection and up to 96% behavior restoration across multiple architectures.
-
Measuring User's Mental Models of Speech Translation in Human-AI Collaboration
A cross-lingual QA framework shows users build stronger mental models of MT systems through practice and source language knowledge mainly by spotting surface-level errors, with transcriptions helping further.
-
Test-Time Training with Next-Token Prediction
TTT-NTP adapts pretrained LLMs at test time by training fast weights to match next-position hidden states from the forward pass, yielding consistent gains on long-context benchmarks across Llama, Mistral, and Qwen models.
-
SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services
SCOPE selects readable hidden layers, constructs conformal gates with IND calibration, and uses supermartingale e-processes to certify persistent service-boundary evidence, improving rejection over final-layer detectors across multiple LLMs and boundary conditions.
-
ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation
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.
-
PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation
PiDA generates phonetically similar corruptions for fine-tuning NMT on FLEURS Vietnamese-English, improving translation of ASR errors by up to +2.04 BLEU while slightly boosting clean performance.
-
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics correlating to LLM judges.
-
GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.
-
ArabiGEE: A Hierarchical Taxonomy for Arabic Grammatical Error Explanation
ArabiGEE introduces the first hierarchical taxonomy for Arabic grammatical error explanation, with 27 error types, 140 correction types, and 324 explanations, applied to annotate corpora and evaluate LLMs.
-
Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR
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.
-
Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation
A systematic analysis of 284 manually reviewed papers plus 1.8k+ others from 2023-2025 reveals under-reporting of human evaluation study design details, creating ambiguity in what was measured and how.
-
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
EmbedFilter applies a linear filter derived from the LLM unembedding matrix to suppress high-frequency token influences in text embeddings, yielding improved zero-shot performance and inherent dimensionality reduction.
-
Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection
EGC reveals that graph consistency measures align with hallucinations in Llama-2 but reverse direction in GPT-4, GPT-3.5 and Mistral-7B on the RAGTruth QA split, indicating model-family-specific hallucination patterns.
-
ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs
ReverseEOL improves training-free text embeddings by combining forward and reversed-text representations from frozen decoder-only LLMs.
-
Boosting Self-Consistency with Ranking
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
-
Caliper: Probing Lexical Anchors versus Causal Structure in LLMs
Lexical anonymization via Caliper causes consistent accuracy drops of 7-30 percentage points across LLMs on causal benchmarks, indicating reliance on lexical anchors rather than structural causal reasoning.
-
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
CRAFT is a Pareto-front prompt optimizer that allocates scarce LLM validation calls to candidates near the current front using accuracy- and cost-oriented generators plus NSGA-II retention.
-
Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA
Introduces DOSEBENCH benchmark and shows four LLMs often fail at rolling 24-hour dose calculations and constraint adherence in OTC dosing decisions despite appearing confident.
-
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
Large-scale evaluation shows retrieval-augmented generation yields only marginal and inconsistent gains (1-2 points) over no-retrieval baselines in biomedical QA, with model choice dominating retriever or corpus effects.
-
Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark
Explicit gender cues induce bounded but systematic decision flips in LLMs on value trade-offs, with self-attributions frequently denying gender influence.
-
Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
Peer agreement misleads initially correct LLMs more than it corrects initially wrong ones, with authority labels biasing choices independently of accuracy and reasoning prompts failing to mitigate the asymmetry.
-
Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs
A graph-based MIS prompt selection method on embedding similarity graphs yields reduced benchmark subsets with highly consistent LLM rankings (Kendall's W ≥ 0.90 in 99.2% of cases) and 25-48% size reduction at higher thresholds.
-
A Finite-Calibration Regime Map for LLM Judge Panels
The paper introduces a finite-calibration regime map and Finite-Calibration Panel Selection selector, finding scalar aggregation wins on most real benchmark-budget combinations while joint tables help when interactions are present.
-
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
Parameter-based knowledge editing in LLMs induces reasoning collapse via dimensional collapse and is consistently outperformed by a retrieval baseline across varied edit counts, knowledge complexity, and evaluation metrics.
-
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
LLMs correct only 34.8% of zero-shot annotation errors via prompting, and Definition-Specific Familiarity correlates positively with performance (partial r = +0.41) while memorization metrics do not.
-
The Attentional White Bear Effect in Transformer Language Models
Prohibited concepts remain recoverable from hidden states, influence attention routing, and shape generations in transformers under instruction-based suppression.
-
ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation
ReverseMath uses answer inversion to generate paired original and reversed math problems with known answers for detecting memorization and improving LLM reasoning via data augmentation.
-
Tracing Computation Density in LLMs
LLM computation follows a consistent two-phase pattern: a sparse early-layer core reconstructs the head of the output distribution, with later layers and attention heads providing incremental refinements that correlate with model uncertainty.
-
Probing Minimalist Phase Structure in LLMs: What Universal Dependencies Cannot Represent
Structural probes on UD-invariant wh-movement stimuli reveal phase-count gradients and phase-internal cohesion effects in 12-13 of 13 LLMs, indicating syntactic abstractions beyond UD annotations.
-
Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation
LLMs generate adequate counterspeech for co-occurring hate and misinformation in 40% of cases, with a mixed knowledge strategy from fact-checkers and NGOs proving most effective after expert revision.
-
Token-weighted Direct Preference Optimization with Attention
AttentionPO weights tokens in DPO using LLM attention as a pairwise judge, yielding better results on AlpacaEval, MT-Bench, and ArenaHard than prior preference optimization methods.
-
Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale
LLM-rephrased synthetic clinical notes preserve core information and utility for coarse prediction tasks but lose fine-grained details such as ICD codes, with chunk-wise rephrasing as a partial mitigation that trades off factual accuracy.
-
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
Vocabulary adaptation via targeted token addition and replacement improves semantic similarity, domain word usage, and training efficiency for LLM summarization in legal and medical domains.
-
Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
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.
-
Calibrating LLMs with Semantic-level Reward
CSR improves LLM calibration by combining binary correctness rewards with a semantic calibration reward that promotes agreement on correct rollouts and discourages spurious consistency on incorrect ones, outperforming verbalized confidence baselines on ECE and AUROC across in- and out-of-domain QA任务
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.