HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks

• URL: http://arxiv.org/abs/2607.18867v1
• Date: Tue, 21 Jul 2026 08:58:36 GMT
• Title: HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks
• Abstract summary: We present HindsightBench, a behavioral audit protocol that profiles parametric hindsight at probe-level cost.<n>Applying it to 15 models from seven vendors on a 258-node vintage-correct macro panel yields three headline patterns.<n>We release the panel, frozen preregistrations, per-model audit rows with measured dollar costs, transcripts, and one-command regeneration.
• Score: 1.416562653124415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks. Existence is settled; what users lack is a cheap way to audit a given model for it. We present HindsightBench, a black-box behavioral audit protocol that profiles parametric hindsight in any time-indexed LLM decision task at probe-level cost (no backtests, no logprobs, no corpus access). The protocol chains a four-arm date-manipulation matrix (revealed/date-only/masked/transplanted), dual memory probes (date recovery; outcome recall), and six per-model metrics -- trigger strength, transplant effect, post-cutoff placebo, recoverability, behaviorally effective knowledge cutoff, and a recall-accuracy dissociation coefficient -- with explicit gates where identifiability is data-dependent. Applying it to 15 models from seven vendors on a 258-node vintage-correct macro panel yields three headline patterns: (i) the date-trigger reflex tracks training generation, not scale -- absent across the 2024 open-weight generation from 1B to 70B, present in every tested 2026-generation model, and switching on within one vendor lineage (Qwen3 -> Qwen3.6) at fixed MoE architecture and 3B active parameters; (ii) effective cutoffs span 22 months across vendors and precede vendor-reported dates by up to eight months, invalidating calendar-window placebo designs; (iii) audit results are not invariant to serving -- BF16 serving of an FP8-referenced model breaks the trigger estimate's stability while AWQ-INT4 preserves it, and a provider-locked reasoning regime makes one probe non-convergent -- so the protocol ships with operational requirements (pin quantization and thinking regime; disclose parser and sampling policy). We release the panel, frozen preregistrations, per-model audit rows with measured dollar costs, transcripts, and one-command regeneration.

Related papers

• State of Thought Enables Endogenous Reasoning [48.902117018115256]
  Test-time reasoning has emerged as a major approach to improving the capabilities of Large Language Models (LLMs)<n>We propose State of Thought, a new reasoning paradigm that enables endogenous reasoning in LLMs.<n>We show that SoT consistently improves mean-baseline accuracy while reducing generated tokens by 62.6% and end-to-end latency by 44.6%.
  arXiv  Detail & Related papers  (2026-09-13T05:55:03Z)
• MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models [49.47300047353726]
  We introduce MemToC, a benchmark for post-tool-return arbitration with executable tools.<n>MemToC comprises 6,504 evaluation episodes constructed from 542 quality-controlled factual questions.<n>Across five open-weight 7-9B models, tool returns strongly dominate elicited closed-book answers.
  arXiv  Detail & Related papers  (2026-08-26T18:22:03Z)
• BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice [4.108510562556002]
  Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic constraints on risk, fees, and diversification.<n>We study a model-agnostic, asset-agnostic post-generation guardrail pipeline.<n>We introduce BiasMix-Finance (Mini), a compact stress-test benchmark for constrained decision-making under biased generations.
  arXiv  Detail & Related papers  (2026-08-14T05:32:14Z)
• Right Knowledge, Wrong Answer: Test-Time Steering for Temporal Fact Conflicts in Open-Weight Language Models [2.11832654407998]
  Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdated answer.<n>We formalize this problem as Parametric Temporal Conflict (PTC) and introduce Temporal Attractor Steering (TAS)<n>TAS detects likely conflicts, identifies a conflict-critical layer, and steers hidden states toward newer-fact representations without retraining or external retrieval.
  arXiv  Detail & Related papers  (2026-06-18T21:56:18Z)
• ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking [2.2573512203799626]
  We propose ReacTOD, a bounded neuro-symbolic architecture that reformulates NLU as discrete tool calls within a self-correcting ReAct loop governed by deterministic validation.<n>A bounded ReAct loop enables iterative self-correction, improving accuracy by up to 9.3 percentage points over single-pass inference on MultiWOZ.
  arXiv  Detail & Related papers  (2026-05-18T20:06:04Z)
• Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers [0.0]
  Large language models (LLMs) typically approach optimization as an inference-time procedure, solving each instance separately.<n>We study this question on Synergistic Dependency Selection (SDS), a controlled variant of constrained Quadratic Knapsack.<n>We fine-tune Qwen2.5-Coder-14B-Instruct with Group Relative Policy Optimization using a feasibility-gated reward and light structural scaffolding.
  arXiv  Detail & Related papers  (2026-05-18T13:21:40Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• TEMPO: Scaling Test-time Training for Large Reasoning Models [87.61789183311856]
  Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time.<n>We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled dataset.
  arXiv  Detail & Related papers  (2026-04-21T10:01:04Z)
• SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio [0.038379177968040606]
  We propose SELFDOUBT, a single-pass uncertainty framework for reasoning language models.<n>Our key signal, the Hedge-to-Verify Ratio (HVR), detects whether a reasoning trace contains uncertainty markers and, if so, whether they are offset by explicit selfchecking behavior.<n> SELFDOUBT operates on a single observed reasoning trajectory, making it suitable for latency- and cost-constrained deployment over any proprietary API.
  arXiv  Detail & Related papers  (2026-04-07T19:19:29Z)
• Self-Calibrating Language Models via Test-Time Discriminative Distillation [18.46710400838861]
  Large language models (LLMs) are systematically overconfident on questions they often answer incorrectly.<n>We introduce $textbfSECL$ ($textbfSE$lf-$textbfC$alibrating $textbfL$anguage Models), a test-time training (TTT) pipeline that exploits this gap as label-free self-supervision.
  arXiv  Detail & Related papers  (2026-03-18T13:28:50Z)
• ZIP-RC: Optimizing Test-Time Compute via Zero-Overhead Joint Reward-Cost Prediction [57.799425838564]
  We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost.<n> ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost.
  arXiv  Detail & Related papers  (2025-12-01T09:44:31Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Error-based Knockoffs Inference for Controlled Feature Selection [49.99321384855201]
  We propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees.
  arXiv  Detail & Related papers  (2022-03-09T01:55:59Z)

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.