Open Problems

Language Model Evaluation & Benchmarking

Multi-Model Evaluation and Ensembling Without Per-Step White-Box Logit Access

Barrier to removePartly addressed
Possible candidate · 2/5 runs3 papers report this100% from 2025+

Generated automatically from the limitations stated in 3 papers (ACL, EMNLP), listed under Evidence. It is not a paper, and it does not come from papers submitted to CSPaper.

The problem

Current multi-model evaluation and collaborative generation frameworks require synchronous, step-by-step execution across multiple 32B–70B open-source LLMs with direct access to intermediate token logits. This white-box precondition structurally excludes closed-source, API-only models (which do not expose unconstrained per-step logits) from participating in these evaluation pipelines. It also prevents deployment on resource-constrained hardware unable to fit multiple large model footprints into memory simultaneously. Consequently, these benchmarking and decoding techniques cannot be applied to leading proprietary models or decentralized, asynchronous workflows.

Why it matters

Enables multi-model ensembling and evaluation methods to incorporate proprietary API models and run on consumer-grade hardware. It removes the dependency on dedicated multi-GPU clusters for multi-model verification.

Ways to approach it

Prior-work checks are free with an account. Results someone already ran are shown to everyone.

  1. 1

    Sequence-level rank and consensus aggregation: Implement black-box ensembling protocols that operate solely on final candidate sequences and sequence-level confidence signals rather than per-step token logits, measuring output quality and metric correlation against synchronous logit-based baselines across standard reasoning benchmarks (e.g., MMLU, GSM8K).

  2. 2

    Asynchronous cascading verification: Build a pipeline where small local models generate candidate responses that are asynchronously evaluated or filtered by API endpoints, measuring latency, memory usage, and task accuracy relative to synchronous multi-model decoding.

  3. 3

    Lightweight surrogate calibration: Use a single compact local model (e.g., 3B–8B) to approximate ensemble distribution shifts from black-box text samples, evaluating the degradation in scoring fidelity against full 32B/70B multi-model ensembles.

Have a different approach?

Describe how you would tackle this problem and we'll look for papers that already do it. Free; your text stays private.

Free · 3 checks per day

Why it might fail

If fine-grained token logits contain high-entropy calibration information that cannot be approximated or recovered from sampled text outputs and top-k logprobs, black-box approaches will consistently underperform white-box ensembles. Furthermore, if API providers standardize full intermediate state access, the motivation for black-box ensembling algorithms will diminish.

Evidence

Each paper's own statement of the limitation, verbatim.

Nearest existing work

Related open problems

Language Model Evaluation & Benchmarking

Barrier to removeOpen

Methods and Benchmarks for LLM Judging, Ranking, and Evaluation That Work Without Token-Level Probabilities

A large fraction of scoring, ranking, and error-detection techniques for LLMs depend on logprobs, logits, or perplexities, which commercial APIs increasingly do not expose. This structurally blocks researchers and practitioners using closed models from applying state-of-the-art evaluation and ranking methods, forcing them onto weaker text-only alternatives or into hosting expensive open models. There is currently no systematic account of how much quality is lost when moving from probability-based to text-only judgments, nor of which probability signals can be reliably elicited from a model's own generated text.

Possible candidate · 2/5 runs7 papers report this100% from 2025+

Language Model Evaluation & Benchmarking

Barrier to removeOpen

Label-Free and Transferable Calibration for Large Language Model Outputs

Existing calibration and uncertainty quantification techniques for large language models (LLMs) strictly require task-specific, ground-truth-labeled calibration sets with binarizable correctness annotations. In open-ended, domain-specific, or novel tasks where ground-truth labels do not exist or cannot be easily thresholded, these methods cannot be instantiated. Consequently, practitioners are structurally blocked from obtaining calibrated confidence scores, prediction intervals, or coverage guarantees for LLMs without first performing expensive per-task and per-model annotations.

Possible candidate · 2/5 runs5 papers report this100% from 2025+

Language Model Evaluation & Benchmarking

Barrier to removeOpen

Probability-Free LLM Evaluation and Benchmarking for Black-Box Models

Many standard evaluation, uncertainty estimation, and benchmarking techniques rely on token-level log-probabilities or soft output distributions. Proprietary and closed-access models (e.g., commercial chat interfaces and restrictive API endpoints) often only expose discrete text outputs, completely excluding them from probability-dependent benchmark comparisons. Relying on Monte Carlo sampling frequencies as a fallback is computationally prohibitive and prone to distortion from proprietary sampling temperatures or top-$p$ truncations. Consequently, existing evaluation suites cannot rigorously compare open-weight and closed-access models under a uniform probability-dependent protocol.

Strong candidate · 5/5 runs4 papers report this25% from 2025+
Generated automatically, not curated by hand. Automated prior-work checks catch about a third of existing work, so treat this problem as a lead to investigate.