cs.CVOct 28, 2026
SaveHidden Commitment: When Language Models Silently Pick a Side and How Steering Can Surface It
Organizations: KAIST, School of Computing, Daejeon, South Korea. · Konkuk University, School of Electrical and Electronics Engineering, Seoul, South Korea.
Abstract
Language-model answers are often treated as a visible record of the internal decision that produced them. We test this assumption in conflicting-context question answering, where two supplied documents support incompatible answers. A model can process the disagreement and still return a one-sided answer, even under prompts that ask it to disclose conflict. In Qwen 0.8B, hidden source commitment is captured by a residual source-choice direction whose sign tracks which document the answer uses. Sparse middle-layer MLP writers feed the same coordinate, and steering the coordinate changes the chosen source. A transfer run on Gemma 3 1B preserves the source-choice readout and sparse-write bridge under LLM-audited labels. Conflict disclosure follows a different pattern, appearing weaker, later-layer, and only partially steerable. These results support a practical monitoring strategy for retrieval systems that detects silent source commitment with residual readouts and pairs conflict-surfacing prompts with disclosure steering when the model has selected a side under disagreement.
Figures & tables
Figure 1: Source-selection steering under conflicting context. A question is paired with two long documents that support incompatible answers. Document 1 states that Ireland gained independence in , while Document 2 states . The baseline model gives a one-sided answer from Document 2. At generation time, we add a learned source-selection direction to the layer- residual stream on the decision token, shifting the activation from the Document 2 side of the doc-choice axis toward the Document 1 side. The steered model then answers from Document 1.
Figure 2: Residual sign tracks answered source in both models. Colors encode presentation order, so the separation cannot be reduced to a first-document or truth readout.
Figure 3: The source-choice readout is answer-span aligned. The strongest validation AUROC appears at decision-token positions and peaks at mean_decision . The layer/position sweep shows the same band of high readout performance across middle layers near the answer span, with the selected layer- direction marked.
Figure 4: Residual steering of the source-selection axis. The curve aggregates original and swapped held-out rows. Error bars are Wilson confidence intervals over decided rows. The table shows a representative source flip.
Figure 5: Sparse MLP writes align with the residual source-selection state. CETT-localized writes project onto the learned source-choice direction in both models. Layer-distribution histograms are in Figure 14 .
Figure 6: Sparse MLP writers feed the source-choice residual state. CETT localizes MLP neurons whose activations distinguish source choice, and the write-projection test asks whether their residual updates align with the learned source-choice direction.
Figure 7: Matched controls for conflict specificity. Agreement and single-document controls reduce sparse-write magnitude relative to contradiction.
Figure 8: Closed-book unknown subset. The contradiction gap remains when closed-book recall is unlikely to dominate.
Figure 9: Disclosure steering improves conflict surfacing on prompt-matched Qwen failures. Points show transparency lift with Wilson confidence intervals; counts below are on the reproduced prompt-failure rows with closed-book parametric_unknown labels. Surfaced is broad conflict acknowledgment, and No-side subset is strict unresolved disclosure within surfaced rows.
Appendix figures & tables9 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 10: Token positions and intervention windows used in the residual readout and steering analyses. The schematic defines the prompt tail, decision-token region, response-onset positions such as pre_response_last , and the response-time windows used for source-choice and conflict-surfacing interventions.
| Model | Direction / contrast | Layer | Position | Fit rows | Val AUROC | Held-out AUROC |
|---|---|---|---|---|---|---|
| Qwen | Source-choice residual direction, doc2 vs. doc1 | 13 | mean_decision | 235 train (116/119); 54 val | 0.9959 | 0.9945 |
| Gemma | Source-choice residual direction, doc2 vs. doc1 | 12 | last_decision | 238 train (163/75); 61 val | 0.9897 | 0.9806 |
| Qwen | Broad disclosure, conflict-aware vs. plain decided | 17 | pre-resp. last | 727 train (305/422); 243 val | 0.7935 | 0.7670 |
| Qwen | Strict disclosure, unresolved vs. plain decided | 17 | pre-resp. last | 629 train (207/422); 207 val | 0.8397 | 0.8553 |
| Qwen | Anti-collapse, noncommittal vs. effectively decided | 23 | pre-resp. last | 772 train (242/530); 255 val | 0.7591 | 0.8082 |
Table 1: Inventory of reported directions. Parentheses in the fit column give positive/negative counts for the training split. Source-choice positives are document-2 selections; disclosure positives are conflict-aware or noncommittal labels.
Figure 11: Closed-book recall proxy distribution on the usable FaithEval set.
Figure 12: Gemma source-choice transfer. The learned layer- source-choice projection tracks answered source under document-order swap, peaks near the answer span, and is recovered from sparse MLP writes.
Figure 13: Gemma controls and intervention checks. The control panel shows larger internal decision-token polarization for contradictory documents than agreement or single-document controls. Source-choice steering is statistically clear but low-rate.
| Case | Evidence | How it is treated |
|---|---|---|
| Gemma no-op hook sensitivity | Early diagnostic hooks altered generation even when intended as no-op instrumentation. | Excluded from causal claims; valid steering claims use the later fixed-hook response-only run. |
| Low-rate Gemma source steering | At residual scale , localized steering produced source-choice flips versus for random controls, but text changed more often than the flip rate itself: localized outputs versus random outputs. | Report as causal support with a small effect size, not as a full behavioral replication. |
| No Gemma surfacing intervention claim | Gemma surfacing transfer currently supports a readout/timing result, not a robust intervention result. | Keep separate from the Qwen surfacing steering result. |
| Layer-22 / layer-17 surfacing mismatch | The bundled Gemma surfacing figure metadata says layer 22 at response_first4_mean ; the full stratified result says layer 17 at pre_response_last . | Omit the older panel and report the stratified result in text. |
| Leaning vs. unresolved label boundary | The Gemma manual audit changed labels, all from leaning to unresolved, where the judge rationale said both candidates were presented without choosing. | Use strict unresolved labels for the cleanest policy target; report broad surfacing separately. |
Table 2: Failure case gallery and partial-results accounting for Gemma transfer. The table distinguishes evidence retained in the paper from diagnostics that should not be overclaimed.
Figure 14: Layer distribution and sign of CETT-localized MLP writers. These panels are the histogram components removed from the main sparse-write bridge figure so the main text can focus on the write-projection evidence.
Figure 15: Layer-matched random-control distribution for the upstream write-projection test. The random controls are mostly near chance (mean AUROC , median ). Two of random controls match or exceed the CETT set on AUROC, but none match its projection gap.
Figure 16: Layerwise breakdown of the same write-alignment test. The shaded region marks MLP layers upstream of the layer- residual readout. Strong upstream layers appear at layers , , , and with AUROCs , , , and , respectively.
More in this topic
Knowledge Conflicts in Language Models
Knowledge conflicts in language models concern how models reconcile stored knowledge with conflicting context, retrieved evidence, tools, or memory.
See all 143 papers