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 (61%).
641
Pith papers citing it
Background
61% 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 57
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.
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
SkillWeaver formalizes compositional skill routing for LLM agents and introduces SAD, which raises step-level decomposition accuracy from 51% to 67.7% on a new 300-query benchmark over 2209 real MCP skills.
citing papers explorer
-
CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges
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.
-
TW-LegalBench: Measuring Taiwanese Legal Understanding
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.
-
Entropy-Gated Latent Recursion
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.
-
Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation
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.
-
Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
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.
-
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
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: A Structured Dataset for Indian Right-to-Information Decision Analysis
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
-
Privacy Auditing with Zero (0) Training Run
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.
-
Crafting Reversible SFT Behaviors in Large Language Models
LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
-
DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning
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.
-
Backdoor Attacks on Decentralised Post-Training
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: Unveiling a Stealthier Gray-Box Trojan against LLMs
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: A French Medical Question Answering Dataset for Knowledge and Reasoning Evaluation
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.
-
Large Language Diffusion Models
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: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
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: A Challenging, Contamination-Limited LLM Benchmark
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: Monolithic Preference Optimization without Reference Model
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.
-
Evaluating Very Long-Term Conversational Memory of LLM Agents
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
-
Information Dynamics of Language Communication
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 Decides Cosine vs. Rank Metrics for Text Embeddings
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: Hash-based Generative Language Models
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.
-
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
-
Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation
DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
-
Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose
SkillWeaver formalizes compositional skill routing for LLM agents and introduces SAD, which raises step-level decomposition accuracy from 51% to 67.7% on a new 300-query benchmark over 2209 real MCP skills.
-
Models Take Notes at Prefill: KV Cache Can Be Editable and Composable
KV caches function as notebooks of prefilled conclusions, enabling field-level edits that recover decisions (especially with CoT) and position-portable skill composition with near-identical outputs at O(L) cost.
-
Polar: A Benchmark for Evaluating Political Bias in LLMs
Polar is a new cross-context benchmark showing LLM political bias measurements are not fixed but vary with country, issue, model, and language.
-
Small LLMs for Biomedical Claim Verification: Cost-Effective Fine-Tuning, Structural Dataset Shortcuts, and Cross-Domain Generalization
Fine-tuned Mistral-7B via QLoRA achieves up to 12% higher F1 than GPT-4o on biomedical claim verification with 1008 examples, identifies a structural shortcut in SciFact, and shows robust cross-domain transfer from sound data.
-
Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
ICL in LLMs shows a sharp ceiling on categorical distributions for high-cardinality tabular data, failing to reproduce rare classes despite examples, while numerical fidelity improves.
-
INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration
INFRAMIND is an infrastructure-aware multi-agent orchestration framework that uses RL on a hierarchical constrained MDP to jointly optimize topology, model selection, and scheduling under dynamic load.
-
STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
STAR-KV applies differentiable soft thresholding for per-head and per-block adaptive low-rank KV cache compression, combined with hybrid decomposition and low-rank-aware quantization, achieving up to 75% compression and 3.1x throughput gains.
-
SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models
SurgiQ is a new 13k-question surgical benchmark showing general-purpose LLMs reach 68.1% accuracy while most biomedical models lag and smaller models stay near random baseline.
-
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
DICE formalizes multi-agent LLM coordination as discounted incomplete-information Markov games and introduces Heterogeneous Quantal Response Equilibrium (HQRE) to achieve unique stable equilibria with bounded regret, demonstrated via prompt-control and fine-tuning algorithms on eleven benchmarks.
-
Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving
Tangram makes non-uniform KV cache compression practical for LLM serving with deterministic budget allocation, head group paging, and ahead-of-time load balancing, achieving up to 2.6x throughput gains.
-
QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving
QCFuse achieves full-prefill quality in RAG with 1.7x average prefill speedup over full prefill and 1.5x over ProphetKV via compressed query-aware cache fusion.
-
Text-to-Image Models Need Less from Text Encoders Than You Think
A bag-of-position-tagged-words embedding guides text-to-image diffusion models as effectively as full contextual text embeddings from standard encoders.
-
ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models
ClinicalMC is a benchmark of 1,275 Chinese and 5,804 English multi-course clinical samples across four stages, evaluated via a multi-agent framework on closed-source, open-source, and medical LLMs in static and dynamic settings.
-
EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction
Introduces EURO-5K dataset from 136 EU acts and benchmarks full fine-tuning vs QLoRA for BERT and LLM models on reporting obligation extraction, reporting 0.89 F1 with limited gains from legal pretraining except under parameter-efficient adaptation.
-
Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models
Defines representational capacity as the upper bound on distinguishable near-orthogonal directions in transformer latent spaces, derived from embedding similarity distributions and an adjusted Johnson-Lindenstrauss formula dependent on the k/d ratio.
-
Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference
A new fault-injection framework enables a systematic empirical study that produces 17 takeaways on error propagation in LLM inference and four software-only mitigation directions.
-
Locality Does Not Imply Reachability: Boundary Repair in Block-Sparse Causal Attention
Fixed block causal masks create reachability boundaries where representations depend only on block prefixes, formalized via dependency sets and phase-conditioned coverage functions, with a parameter-free boundary bridge repair.
-
CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs
CultureForest benchmark shows top LLMs degrade sharply on open-ended cultural reasoning tasks, exhibit regional disparities, and are limited more by effective use of knowledge than by lack of knowledge itself.
-
Can we trust LLM Self-Explanations for Entity Resolution?
LLM self-explanations for entity resolution are unstable and weakly faithful to causal evidence, but a hybrid framework using them as priors matches post-hoc quality at up to 10x lower cost.
-
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
MENTIS applies layerwise covariance torsion (T1), spectral torsion (T2), and ERA localization to paired IT/PA 7-8B models, finding selective larger shifts for normative concepts, negative correlation with entropy, and mid-to-late layer peaks.
-
Next-Billion AI Index: The compass for AI utility and adoption in the global majority
Introduces nexbax, a diagnostic framework with three themes and 10 dimensions for evaluating AI economic viability, operational practicality, and societal integrity in next-billion-user contexts.
-
Vector Linking via Cross-Model Local Isometric Consistency
A reference-based geometric hashing method recovers cross-model vector correspondences by exploiting local isometric consistency in contrastive embeddings and iteratively bootstrapping from a seed of paired anchors.
-
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
The study links three LVLM architectural dimensions to three hallucination types via a new benchmark, finding that language foundation quality reduces co-occurrence errors, visual encoder strength reduces similarity errors, alignment reduces uncertainty errors, and joint visual-alignment improvement
-
Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs
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.
-
Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models
Introduces SANSA paradigm for semantic-agnostic vision-language segmentation via dictionary or example-based prompts, with finetuning delivering up to 20% mIoU gains on the new task while retaining standard performance.
-
Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
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.
-
MATCHA: Matching Text via Contrastive Semantic Alignment
MATCHA introduces a dual-view contrastive metric measuring proximity to gold text and distance from adversarial contradictions, outperforming ROUGE and BERTScore by up to 20% on TruthfulQA and other NLP benchmarks.