CoT Faithfulness

Vision-language-action (VLA) models generate chain-of-thought (CoT) reasoning alongside driving trajectories, but existing benchmarks evaluate only trajectory quality and do not assess whether the CoT is relevant, consistent, or causally connected to the driving action. We introduce VLADriveBench, a framework that combines observational metrics (mentioning, hallucination, contradiction, action alignment) with a CoT intervention protocol to provide complementary views of the CoT-action relationship. Applying VLADriveBench to three models across two architectures, we find that the two analyses can diverge sharply: ORION scores highest on observational alignment yet its CoT is epiphenomenal, while Alpamayo v1.5 scores lower yet its CoT is strongly causal, with visual salience gating the extent of CoT influence.

Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix. This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking, overt jailbreak, and a distinct failure mode we term context-injection failure (where the CoT maintains safe reasoning, but the visible output produces harm, highlighting a multi-turn manifestation of reasoning unfaithfulness). We evaluate three distilled reasoning targets against a fixed attacker across five oversight conditions, collecting 6750 turn-level observations on the Information-Hazard scenario. Our analysis reveals two reproducible vulnerabilities: an oversight paradox where explicit monitoring cues paradoxically increase alignment-faking rates rather than suppress them, and a context-injection failure where models lock onto unsafe external outputs despite safe internal states. We release the full dataset of multi-turn dialogues and CoT traces to support follow-up trace-diagnostic research.

Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the chain-of-thought stays factually correct from first turn to last while the emitted answer flips wrong. We call this unfaithful capitulation (UC) and isolate it with a $2\times 2$ latent-versus-behavioral framework that flip-rate metrics and single-turn faithfulness probes both miss. Across three datasets (MT-Consistency, MMLU-Pro, GSM8K), the latent-correct rate at the behavioral flip clusters near 50% in think mode and collapses to 11-15% under no_think -- paired, within-model causal evidence that reasoning creates the gap. Across models the effect tracks the reasoning channel (high in Qwen3-32B and GPT-OSS-20B, low in inline-CoT Gemma-4-31B-it). An independent GPT-4o judge corroborates $86\%$ of UC labels; a token-level probe shows the answer-slot argmax is correct in $84\%$ of UC cells; and a naive trace-anchored defense backfires. We release all trajectories, traces, and judge labels.

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model families. We present the first large-scale evaluation of CoT monitorability across 13 diverse languages and seven frontier model families, comprising 16 models. Using adversarial-hint evaluations that require explicit intermediate computation, together with analysis of internal answer-token probabilities, we consistently find CoT unfaithfulness across languages and hint types, with an average rate of 95.9% across 8B--120B parameter models. We find that frontier models systematically exhibit strategic manipulation, including answer-switching, post-hoc rationalization, and procedural exploitation of hints, making their reasoning difficult to reliably monitor. These deceptive patterns remain especially pronounced in low-resource languages, revealing fundamental limitations in current CoT-based oversight. Our results show that CoT monitoring is fragile under linguistic distribution shift, providing a substantially weaker safety signal than English-only studies suggest. These findings motivate the development of more robust CoT monitors and complementary white-box monitoring techniques, particularly for mid- and low-resource languages. Our code is available \href{https://multilingual-cot-monitoring.github.io/}{\textcolor{blue}{here}}.

When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved this choice depends on how well-known the fact is. We ask: does the model's chain-of-thought (CoT) reasoning faithfully report this mechanism? We introduce introspective faithfulness and test it across 200 questions, 8 models, and 4 prompt conditions. We find CoT reasoning is highly stable across opposite decisions: flip pairs retain 96% of same-answer similarity (d=0.34; confirmed by ROUGE-L, d=0.45). Yet self-rated confidence carries a faint genuine signal: for obscure facts where entity fame is uninformative, confidence still predicts decisions (p<0.001) and tracks item-level knowledge (r=0.134). GPT-4o is the only model with statistically reliable reasoning-decision coupling. Claude Sonnet 4.6 shows the widest confidence range (SD=1.39) but near-zero pooled correlation because the confidence-decision relationship reverses between conditions; a temperature ablation confirms this is model-specific. Internal thinking tokens show greater decision-sensitivity than user-facing CoT (p=0.033). CoT decomposes into a decision-invariant knowledge display (~96%) and a thin confidence layer with weak but real signal. For monitoring: read confidence, not the argument.

Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faithfulness assessment methods are either unscalable, expensive, or unreliable. We propose GeoFaith, a spatio-temporal framework that leverages latent geometric structure and entropy dynamics to diagnose and enforce faithful reasoning. We develop a scalable bootstrapping pipeline expanding step-level annotations from 1k to 20k samples across four domains, train an 8B faithfulness detector outperforming GPT-5 on standard benchmarks, and design a faithfulness-aware reinforcement learning framework jointly optimizing outcome correctness, process faithfulness, and trajectory consistency. Experiments show the proposed method achieves superior performance on both faithfulness detection and downstream reasoning, producing shorter, more interpretable chains without sacrificing accuracy. Our code will be made available publicly.

Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual decision process. Existing CoT unfaithfulness detectors mainly rely on external signals from generated rationales, such as textual plausibility or answer consistency, while overlooking evidence from the model's internal computation. Although recent circuit tracing methods provide a way to obtain model-internal evidence by tracing how information flows through model components during reasoning, constructing full reasoning circuits for long CoTs is costly and difficult to scale. To address these challenges, we propose Circuit-guided Internal-External Discrepancy Scorer (CIE-Scorer), a framework for instance-level CoT unfaithfulness detection. The key idea is that faithful reasoning traces should align with the model's computational process, whereas unfaithful traces may diverge from it. CIE-Scorer efficiently traces compact sentence-level circuits from informative reasoning tokens, constructs internal and external reasoning graphs, and measures their discrepancy using Fused Gromov--Wasserstein distance. Experiments on four datasets from FaithCoT-Bench show that CIE-Scorer achieves state-of-the-art performance while reducing the cost of circuit construction, demonstrating the effectiveness of combining mechanistic interpretability signals with external reasoning traces for CoT unfaithfulness detection.

Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions. Several faithfulness metrics have been proposed, but whether they indeed measure faithfulness remains unknown. Answering this requires ground-truth labels, which are hard to obtain since internal computations are not directly observable. Consequently, most works proposing metrics report only absolute scores or comparisons to prior metrics, and the few existing benchmarks rely on proxies like plausibility or importance, properties orthogonal to faithfulness that can mislead about whether a CoT can be trusted. We address this challenge by constructing tasks whose outputs reveal which intermediate computations must have produced them, and developing an automated labeling pipeline that yields ground-truth faithfulness labels at both the step and CoT level. Building on this methodology, we present BonaFide, a benchmark of 3,066 labeled CoTs across 13 tasks and 10 models, and use it to conduct the first systematic evaluation of prominent faithfulness metrics. Our experiments show that most metrics perform near chance, exhibit strong prediction biases and degrade on longer CoTs. The best metric reaches only 0.70 AUROC at the CoT level while another reaches 0.59 at the step level, with neither transferring across settings, while entailing prohibitively high computational cost. Our results expose fundamental gaps in current faithfulness evaluation and call for the development of more reliable and efficient metrics.

Chain-of-Thought (CoT) faithfulness, i.e., whether CoTs genuinely reflect large language models' (LLM) underlying behavior, is typically evaluated under two disjoint paradigms: contextual faithfulness, measured by perturbing the input or CoT trace, and parametric faithfulness, assessed by intervening on a model's parametric knowledge. Yet prior work compares them only descriptively. We fill this gap by proposing FaithMate, a unified preference-alignment interface for optimizing models towards either faithfulness paradigm. It enables us to investigate the interplay between the two paradigms, examining whether and to what extent faithfulness gains generalize within and across paradigms. Across three models, two datasets, and six faithfulness metrics, we find that the two paradigms are positively coupled, yet asymmetric: optimizing towards parametric faithfulness yields consistent gains across both paradigms, whereas the contextual counterpart delivers more variable gains. Within the contextual paradigm, faithfulness gains on one metric do not consistently transfer to others, implying that existing contextual metrics capture disjoint facets of faithfulness and exposing inherent trade-offs. These findings imply that CoT faithfulness is not a monolithic objective and therefore requires multifaceted optimization and evaluation.

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass the CoT, making the visible reasoning trace misleading even when it appears plausible. We study CoT faithfulness through a structural information-flow perspective: faithful reasoning should route answer-relevant information through the mediated path from prompt to CoT to answer, rather than through a direct prompt-to-answer shortcut. This perspective yields a task-agnostic framework based on three complementary properties, sufficiency, completeness, and necessity, which we instantiate with entropy-based, masked-KL, and gradient-based diagnostics. We show that these metrics recover externally judged faithfulness differences in hinted reasoning, and identify a low-entropy failure mode of KL-based diagnostics where gradient-based measures remain more stable. Building on this analysis, we introduce update-time interventions for verifier-based on-policy RL, including attention masking, backward-only gradient masking, CoT gradients, and adversarial perturbations of prompt representations. Across hinted arithmetic, reward-hackable code repair, and DAPO-Math models trained without hints but evaluated under wrong-hint injection, our interventions shift behavioral and structural indicators toward stronger CoT mediation. In particular, they make shortcut and reward-hacking behavior more transparent in the CoT and improve task-agnostic faithfulness metrics, while in some settings also reducing wrong-hint susceptibility. Our results suggest that controlling information flow during training is a practical route toward more faithful and monitorable CoT reasoning. Code is available at https://github.com/safety-research/faithful-cot.

Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does CoT contribute if not logical sequencing? In three 1-3B instruction-tuned LMs on GSM8K, we isolate the answer-readout stage via prefix completion and identify a positional shortcut: the model copies whichever number occupies the trailing position before the answer delimiter, regardless of intermediate reasoning. Gold-answer presence accounts for 54-92 pp of accuracy (89-92% of each model's teacher-forcing ceiling); even on incorrect items, the final answer matches the last CoT number 95-96% of the time. The copy channel takes precedence over retained-context completion: replacing the trailing number with a wrong value collapses accuracy to near-zero despite correct intermediates, yet removing it recovers 5-32 pp above that floor--even single-step arithmetic the model can otherwise perform is suppressed when a copyable number is present. Qwen and Llama copy novel distractors 87-95% of the time; Gemma gates selectively. Head-level ablation implicates architecture-specific head sets; the effect replicates on GSM-Symbolic. On non-arithmetic BBH tasks, shuffle retention drops sharply; at 7-8B, content-selective gating emerges. Step-level faithfulness evaluations risk conflating positional answer transport with genuine computation--a failure mode for CoT-based oversight.

We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios. Our main finding is that output natural-language rationales with trajectories may be significantly unfaithful: (i) overall reasoning fidelity is only 42.5%, with Chain-of-Causation matching scene reality less than half the time; (ii) 94 missed pedestrians in one-third of pedestrian-relevant scenes; (iii) 97.7% trajectory fragility under mild visual perturbations; and (iv) only 48.3% mean reasoning-action consistency, with 53.3% of inferences exhibiting low consistency, including 37.9% of stop-claimed cases where the model continues instead. We formalize faithfulness information-theoretically, define entity and action fidelity with verification criteria, and outline a four-component safety architecture aligned with these results.

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We test this assumption with a step-level Detect-Classify-Compare framework built around an answer-commitment proxy that is cross-validated with Patchscopes, tuned-lens probes, and causal direction ablation. Across nine models and seven reasoning benchmarks, latent commitment and explicit answer arrival align on only 61.9% of steps on average. The dominant mismatch pattern is confabulated continuation: 58.0% of detected mismatch events occur after the answer-commitment proxy has already stabilized while the trace continues producing deliberative-looking text, and a vacuousness analysis shows that the committed answer does not change during these steps. In architecture-matched Qwen2.5/DeepSeek-R1-Distill comparisons, the reasoning pipeline changes failure composition more than aggregate alignment, most clearly at 32B where confabulated steps decrease as contradictory states increase. Lower step-level alignment is also associated with larger CoT utility, suggesting that the settings that benefit most from CoT are often the least temporally faithful. Paired truncation and a complementary donor-corruption test further indicate that much post-commitment text is not load-bearing for the final answer. These findings suggest that CoT can remain useful while still being an unreliable report of when the answer was formed.

Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of reasoning theater: deliberative-looking steps that contribute nothing to correctness. This wastes inference tokens, pollutes interpretability, and obscures what the model actually computed. We introduce ProFIL (Probe-Filtered Reinforcement Learning) to reduce theater, increase chain-of-thought faithfulness, and shrink chain length in a single, drop-in extension to Group Relative Policy Optimization (GRPO). A multi-head attention probe is trained once on the frozen base model to detect post-commitment steps from internal activations alone; during GRPO, rollouts whose probe score exceeds a threshold have their advantage zeroed. Our central finding is that a probe trained on a frozen base, with verifier-derived labels and no human annotation, provides a stable signal that suppresses theater while resisting the RL-obfuscation failure mode predicted by prior work. Across four reasoning domains (GSM8K, LiveCodeBench, ToolUse, MMLU-Redux) and two model architectures (Llama-8B, Qwen-7B), ProFIL reduces post-commitment theater by 11--100%, raises faithful-fraction (e.g., +24pp on LiveCodeBench under an independent Claude 3.7 Sonnet judge), and shortens chains by 4--19%, all while preserving or improving task accuracy. ProFIL also beats a matched length-penalty GRPO baseline, isolating the gain as semantic commitment-detection rather than chain compression. Probe weights, training configurations, and rollouts are released across all four domains.

Corruption studies, the standard tool for evaluating chain-of-thought (CoT) faithfulness, infer which steps are ``computationally important'' from accuracy loss when steps are corrupted. We show that when benchmark chains end with an explicit terminal answer line, as in GSM8K and MATH, these tests largely measure \emph{answer placement} rather than where intermediate computation is carried out. Using matched GSM8K examples, removing only the final answer statement while preserving all reasoning collapses suffix sensitivity by about $19\times$ for Qwen~2.5-3B ($N{=}300$, $p{=}0.022$). Conflicting-answer prompts, which contain correct reasoning but a wrong explicit final answer, drive accuracy to zero or near-zero at 7B across five open-weight model families; wrong-answer following is strong at 3B--7B and attenuates sharply at larger scales. Replications on MATH, within-stable comparisons at 7B, and suffix-free chains show the same pattern in different guises: corruption sensitivity tracks the location of explicit answer text, not a fixed computational depth in the reasoning. Generation-time probes indicate that final answers are rarely early-determined during generation (${<}5\%$ early commitment), yet consumption-time behavior systematically follows explicit answer text. The confound is therefore largely a readout effect when the chain is consumed. We propose a three-prerequisite protocol (question-only control, format characterization, and an all-position sweep) as a practical minimum for future corruption-based faithfulness studies.

Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR reliably represent how a model gets to its answer. In this paper, we develop two metrics for critically examining this assumption: Causal Importance of Reasoning (CIR), which measures the cumulative effect of reasoning tokens on the final answer, and Sufficiency of Reasoning (SR), which measures whether a verifier can arrive at an unambiguous answer based on the reasoning alone. Through experiments with the Qwen2.5 model series and ReasoningGym tasks, we find that: (1) while RLVR does improve task accuracy, it does not reliably improve CIR or SR, calling the role of reasoning in model performance into question; (2) a small amount of SFT before RLVR can be a remedy for low CIR and SR; and (3) CIR and SR can be improved even without SFT by applying auxiliary CIR/SR rewards on top of the outcome-based reward. This joint reward matches the accuracy of RLVR while also leading to causally important and sufficient reasoning. These results show that RLVR does not always lead models to rely on reasoning in the way that is commonly thought, but this issue can be remedied with simple modifications to the post-training procedure.

Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present \textbf{TriEx}, a tri-view explainability framework that instruments sequential decision making with aligned artifacts: (i) structured first-person self-reasoning bound to an action, (ii) explicit second-person belief states about opponents updated over time, and (iii) third-person oracle audits grounded in environment-derived reference signals. This design turns explanations from free-form narratives into evidence-anchored objects that can be compared and checked across time and perspectives. Using imperfect-information strategic games as a controlled testbed, we show that TriEx enables scalable analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do. Our results highlight explainability as an interaction-dependent property and motivate multi-view, evidence-grounded evaluation for LLM agents. Code is available at https://github.com/Einsam1819/TriEx.

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both contributes to and faithfully reflects the processes underlying the model's final answer, rather than merely accompanying it, remains challenging. We introduce AtManRL, a method that leverages differentiable attention manipulation to learn more faithful reasoning through reinforcement learning. By training an additive attention mask that identifies tokens in the CoT crucial for producing correct answers, we derive a saliency reward signal that encourages the model to generate reasoning traces that genuinely influence its final predictions. We integrate this saliency reward with outcome-based rewards within the GRPO framework to jointly optimize for correctness and interpretability. Experiments on GSM8K and MMLU with Llama-3.2-3B-Instruct demonstrate that our approach can identify influential reasoning tokens and enable training more transparent reasoning models.

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and reasoning-trained models from two different model families. We track confidence over Chain-of-Thought (CoT), measure the corrective effect of reasoning, and evaluate the contribution of intermediate reasoning steps. We find that models are prone to answer inertia, in which early commitments to a prediction are reinforced, rather than revised during reasoning steps. While reasoning-trained models show stronger corrective behavior, their gains depend on modality conditions, from text-dominant to vision-only settings. Using controlled interventions with misleading textual cues, we show that models are consistently influenced by these cues even when visual evidence is sufficient, and assess whether this influence is recoverable from CoT. Although this influence can appear in the CoT, its detectability varies across models and depends on what is being monitored. Reasoning-trained models are more likely to explicitly refer to the cues, but their longer and fluent CoTs can still appear visually grounded while actually following textual cues, obscuring modality reliance. In contrast, instruction-tuned models refer to the cues less explicitly, but their shorter traces reveal inconsistencies with the visual input. Taken together, these findings indicate that CoT provides only a partial view of how different modalities drive VLM decisions, with important implications for the transparency and safety of multimodal systems.

Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. This limits the use of CoTs for reliable oversight. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize when CoTs can be used to monitor the factors driving LLM behavior; and (2) two prompting stress-test settings to quantify the extent to which CoT monitorability can be degraded. Extensive experiments show that CoT monitorability is a conditional property affected by the evaluated LLM, monitor LLM, and task characteristics. Across these factors, monitorability is higher when decision-critical factors shape the intermediate reasoning process, rather than merely influencing the final answer. Under stress-test prompting, most evaluated LLMs can intentionally reduce monitorability, mainly on tasks where decision-critical factors are not structurally required by the reasoning process. Overall, MonitorBench provides a basis for further research on AI control, reasoning faithfulness, stress-test monitorability, and monitoring scaffords. The code is available at https://github.com/ASTRAL-Group/MonitorBench.

Evaluating whether explanations faithfully reflect a model's reasoning remains an open problem. Existing benchmarks use single interventions without statistical testing, making it impossible to distinguish genuine faithfulness from chance-level performance. We show that faithfulness is not a fixed property but an operator-dependent quantity that changes with the intervention method used to measure it. We introduce ICE (Intervention-Consistent Explanation), a framework that evaluates explanations against random baselines of equal size under multiple operators. Evaluating 7 LLMs across 4 tasks with deletion and retrieval infill operators, we find that switching operators crosses the positive-evidence threshold in 18% of configurations (5 of 28 attention comparisons), with gaps reaching 44 percentage points. Randomized baselines detect anti-faithfulness (explanations worse than random) in nearly one-third of English deletion configurations, invisible without random comparisons. These patterns persist across 6 non-English languages and 2 attribution methods. The methodology generalizes to step-level chain-of-thought evaluation, where preliminary results on 3 frontier models suggest that high accuracy does not imply faithful reasoning.

Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning text, i.e. models may produce fluent rationales while routing decision-critical computation through latent pathways. We introduce a causal, layerwise audit of CoT faithfulness based on activation patching. Our key metric, the CoT Mediation Index (CMI), isolates CoT-specific causal influence by comparing performance degradation from patching CoT-token hidden states against matched control patches. Across multiple model families (Phi, Qwen, DialoGPT) and scales, we find that CoT-specific influence is typically depth-localized into narrow ''reasoning windows,'' and we identify bypass regimes where CMI is near-zero despite plausible CoT text. We further observe that models tuned explicitly for reasoning tend to exhibit stronger and more structured mediation than larger untuned counterparts, while Mixture-of-Experts models show more distributed mediation consistent with routing-based computation. Overall, our results show that CoT faithfulness varies substantially across models and tasks and cannot be inferred from behavior alone, motivating causal, layerwise audits when using CoT as a transparency signal.

The real-world information sources are inherently multilingual, which naturally raises a question about whether language models can synthesize information across languages. In this paper, we introduce a simple two-hop question answering setting, where answering a question requires making inferences over two multilingual documents. We find that language models are more sensitive to language variation in answer-span documents than in those providing bridging information, despite the equal importance of both documents for answering a question. Under a step-by-step sub-question evaluation, we further show that in up to 33% of multilingual cases, models fail to infer the bridging information in the first step yet still answer the overall question correctly. This indicates that reasoning in language models, especially in multilingual settings, does not follow a faithful step-by-step decomposition. Subsequently, we show that the absence of reasoning decomposition leads to around 18% composition failure, where both sub-questions are answered correctly but fail for the final two-hop questions. To mitigate this, we propose a simple three-stage SUBQ prompting method to guide the multi-step reasoning with sub-questions, which boosts accuracy from 10.1% to 66.5%.

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans. We demonstrate that preference optimization - a key step in the alignment phase - can inadvertently reduce the faithfulness of these explanations. This occurs because the reward model (RM), which guides alignment, is tasked with optimizing both the expected quality of the response and the appropriateness of the explanations (e.g., minimizing bias or adhering to safety standards), creating potential conflicts. The RM lacks a mechanism to assess the consistency between the model's internal decision process and the generated explanation. Consequently, the LLM may engage in "reward hacking" by producing a final response that scores highly while giving an explanation tailored to maximize reward rather than accurately reflecting its reasoning. To address this issue, we propose enriching the RM's input with a causal attribution of the prediction, allowing the RM to detect discrepancies between the generated self-explanation and the model's decision process. In controlled settings, we show that this approach reduces the tendency of the LLM to generate misleading explanations.