MMLU
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
The Shape of Wisdom: Decision Trajectories in Language Models
Announce Type: new Abstract: Language models do not simply choose an answer at the output layer. In a 9,000-trajectory MMLU study across Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, and Mistral-7B-Instruct-v0.3, the score of the answer moves across depth in structured ways. We describe each trajectory with three quantities: the current answer margin, the next-layer change in that margin, and the distance from a decision flip.
UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding
arXiv:2606.07167v1 Announce Type: new Abstract: Meaningful multilingual evaluation must test models in the target language and educational context. Urdu, spoken by more than 230 million people, lacks a broad MMLU-style benchmark built from native educational sources. We introduce UrduMMLU, a benchmark of 26,431 Urdu MCQs across 26 subjects and five domains, collected from native Urdu MCQ banks and public examination PDFs.
When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference
arXiv:2606.08098v1 Announce Type: new Abstract: Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference. We show that piping the signals every sample carries into a delegation-based aggregator (Propagational Proxy Voting, PPV) yields an unsupervised consensus rule that beats majority on MMLU-Pro by +1.5 pp overall and +2.24 pp on the non-trivial subset (paired McNemar p ~ 1.0e-14, n = 8,099).
Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models
arXiv:2606.04109v2 Announce Type: replace Abstract: Context-augmented language model systems often wrap supplied content with labels such as Reference:, Evidence:, Instruction:, Note:, or Example:, but the effect of these labels on reader-model behavior remains underexplored. We introduce a paired fixed-content probe over 500 MMLU-Pro items: each item receives the same misleading answer-bearing assertion under different discourse-role labels, and adoption is measured by whether the model...
Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models
arXiv:2606.04109v1 Announce Type: new Abstract: Context-augmented language model systems often wrap supplied content with labels such as Reference:, Evidence:, Instruction:, Note:, or Example:, but the effect of these labels on reader-model behavior remains underexplored. We introduce a paired fixed-content probe over 500 MMLU-Pro items: each item receives the same misleading answer-bearing assertion under different discourse-role labels, and adoption is measured by whether the model outputs...
Latent Performance Profiling of Large Language Models
Announce Type: replace Abstract: Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data contamination, narrow task scope, and weak alignment with real-world reliability. Benchmark-based evaluations such as MMLU PRO, BBH, or IFEval primarily capture what a model outputs on fixed test sets, not how it processes...
Query Circuits: Explaining How Language Models Answer User Prompts
arXiv:2509.24808v2 Announce Type: replace Abstract: Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific input query in a particular way. We introduce query circuits, which directly trace the information flow inside a model that maps a specific input to the output.
Aryabhata 2: Scaling Reinforcement Learning for Advanced STEM Reasoning
arXiv:2605.28829v2 Announce Type: replace Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understanding across physics, chemistry, and mathematics. Recent large language models perform strongly on common reasoning benchmarks, yet they remain difficult to deploy at scale, where millions of student doubts demand domain-specific, consistently structured problem solving. We introduce Aryabhata...
When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
arXiv:2605.30381v1 Announce Type: new Abstract: Deceptive alignment, in which models maintain accurate internal representations while deliberately producing false outputs, remains a central challenge in AI safety. While strategic deception is the primary long-term concern, synthetic dishonesty - induced via direct optimization on incorrect answers - provides a controlled testbed for studying the representational basis of learned deception.
Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
Announce Type: replace Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks. However, task-level expert selection is often too coarse-grained, since different instances may require different expertise.