Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation

• URL: http://arxiv.org/abs/2606.07616v1
• Date: Fri, 29 May 2026 20:55:15 GMT
• Title: Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation
• Abstract summary: We introduce Item Response Scaling Laws (IRSL), a unified framework that integrates Item Response Theory (IRT) within the scaling law framework.<n>IRSL disentangles latent model ability from question characteristics, factorizing the scaling law estimation for $M$ models and $N$ questions.<n>We validate our approach across two prevalent scaling paradigms: (1) pre-training downstream scaling, using 6,612 LM checkpoints and 37,682 questions from 10 benchmarks; and (2) test-time scaling, using 12 LMs and 120 questions from 4 benchmarks with up to 2,500 samples per question.
• Score: 31.553914838498667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scaling laws provide a fundamental framework for understanding the performance of Language Models (LMs), yet deriving them requires prohibitively expensive evaluations across thousands of checkpoints or millions of inference samples. To address this, we introduce Item Response Scaling Laws (IRSL), a unified framework that integrates Item Response Theory (IRT) within the scaling law framework. Unlike traditional approaches that treat each model-benchmark pair in isolation, IRSL disentangles latent model ability from question characteristics, factorizing the scaling law estimation for $M$ models and $N$ questions to significantly reduce parameter complexity from $O(M \times N)$ to $O(M + N)$. We instantiate IRSL with Beta-IRT, which leverages the empirical probability responses of LMs -- such as token probabilities in pre-training and pass rates in test-time sampling -- to capture richer signals than binary responses. We validate our approach across two prevalent scaling paradigms: (1) pre-training downstream scaling, using 6,612 LM checkpoints and 37,682 questions from 10 benchmarks; and (2) test-time scaling, using 12 LMs and 120 questions from 4 benchmarks with up to 2,500 samples per question. Given a one-time calibration on existing model responses, IRSL yields more reliable scaling estimates using only 50 questions per benchmark (a 99.9\% reduction), achieving comparable or superior decision accuracy to traditional approaches. Furthermore, we show that the estimated latent model abilities are generalizable, enabling accurate performance forecasting across benchmarks that share the same measurement objective.

Related papers

• ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling [60.48279351544583]
  ThinkRetrieve is a test-time scaling framework for large reasoning models.<n>It retrieves relevant exemplars at each intermediate step and injects them directly into the thinking trace.<n>It consistently improves accuracy over standard test-time scaling.
  arXiv  Detail & Related papers  (2026-08-11T13:58:07Z)
• Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization [13.903045659324187]
  We propose ScaleQ-1.58, a scalable ternary post-training quantization framework for reasoning LLMs.<n>It is formed by simply integrating AYOT with CAT-Q, which demonstrates several scaling properties.<n>It generalizes well to both dense and MoE architectures, with performance improving as model scale increases.
  arXiv  Detail & Related papers  (2026-08-02T08:22:43Z)
• $V_1$: Unifying Generation and Self-Verification for Parallel Reasoners [69.66089681814013]
  $V_$ is a framework that unifies generation and verification through efficient pairwise ranking.<n>$V_$-Infer improves Pass@1 by up to $10%$ over pointwise verification.<n>$V_$-PairRL achieves $7$--$9%$ test-time scaling gains over standard RL and pointwise joint training.
  arXiv  Detail & Related papers  (2026-03-04T17:22:16Z)
• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• ATTS: Asynchronous Test-Time Scaling via Conformal Prediction [112.54016379556073]
  Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency.<n>We introduce ATTS (Asynchronous Test-Time Scaling), a statistically guaranteed adaptive scaling framework.<n>We show that ATTS delivers up to 56.7x speedup in test-time scaling and a 4.14x throughput improvement.
  arXiv  Detail & Related papers  (2025-09-18T16:55:09Z)
• The NazoNazo Benchmark: A Cost-Effective and Extensible Test of Insight-Based Reasoning in LLMs [3.9977256267361754]
  We present Nazonazo, a cost-effective benchmark built from Japanese children's riddles to test insight-based reasoning.<n>No model except for GPT-5 is comparable to human performance, which achieves a 52.9% mean accuracy.
  arXiv  Detail & Related papers  (2025-09-18T07:50:04Z)
• Adaptive Rectification Sampling for Test-Time Compute Scaling [10.160759436445526]
  We propose Adaptive Rectification Sampling (AR-Sampling) to help models rectify errors at a more fine-grained level.<n>Our approach enables the models to rethink in more fine-grained level, improving the accuracy of solutions, while generating a reasonable number of tokens.
  arXiv  Detail & Related papers  (2025-04-02T02:57:52Z)
• Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? [61.85289698610747]
  We study whether o1-like large language models (LLMs) truly possess test-time scaling capabilities.<n>We find that longer CoTs of these o1-like models do not consistently enhance accuracy.<n>We propose Shortest Majority Vote, a method that combines parallel scaling strategies with CoT length characteristics.
  arXiv  Detail & Related papers  (2025-02-17T07:21:11Z)
• MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity [23.69657750691825]
  We propose MARM (Memory Augmented Recommendation Model), which explores a new cache scaling-laws successfully.<n>For a RecSys model, compared to model parameters, the computational complexity FLOPs is a more expensive factor that requires careful control.
  arXiv  Detail & Related papers  (2024-11-14T13:22:41Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.