大型語言模型預測器所知但未說之事：探測內部表徵以實現校準與忠實性

摘要

針對預測任務進行微調的大型語言模型，雖然能達到準確預測，但校準能力可能不佳，且其思維鏈推理未必能忠實反映預測背後的證據。我們探討內部表徵是否能為此兩者提供更直接的觀察窗口。透過在 OpenForesight 上使用 Eternis-Forecaster 8B 模型，我們訓練了基於中間層激活值的表示池化探針，發現這些探針能達到顯著更佳的校準效果；此結果同樣適用於 GLM-4.7-Flash 與 GLM-4.5-Air 模型。接著，我們透過證據消融與干擾注入來評估思維鏈的忠實度：移除提示中具影響力的來源時，往往會改變模型的預測結果，但推理歷程卻不受影響。相同的探針可作為謊言偵測器：其激活值追蹤行為變化的能力遠優於推理歷程，且在 84% 的案例中能預測變化方向，包括當思維鏈隱藏干擾影響時。最後，強制回答實驗顯示，預測結果在推理開始前就已大致確定：僅需單次推理前的傳遞，即可還原已確定的答案與信心程度；而依據此預設答案分佈的離散程度來分流問題，可節省 30% 至 47% 的生成 token 數量，且準確率不受影響。綜合以上結果，本研究確立了探測內部表徵作為一種實用工具，可廣泛應用於語言模型預測器與推理模型的校準、稽核及分流作業。

English

Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast. We ask whether internal representations offer a more direct window into both. Working with Eternis-Forecaster 8B on OpenForesight, we train representation-pooling probes on intermediate activations and find they achieve substantially better calibration; a result that also holds for GLM-4.7-Flash and GLM-4.5-Air. We then assess CoT faithfulness through evidence ablation and diversionary injection: removing an influential source in the prompt often changes the model's forecast while leaving the reasoning trace untouched. The same probes function as lie detectors: their activations track behavioral shifts far better than the reasoning trace does, and they also predict the direction of change in 84% of cases, including when the CoT conceals the perturbation's influence. Finally, forced answering reveals that forecasts are largely fixed before reasoning begins: a single pre-reasoning pass recovers the committed answer and confidence, and routing questions by the spread of this pre-set answer distribution saves 30-47% of generated tokens, with no loss of accuracy. Together, these results establish probing internal representations as a practical tool for calibrating, auditing, and triaging language model forecasters and reasoning models more broadly.