Causal Reasoning in Language Models

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 57

Oct 4, 2026cs.AI

Readable Before Actionable: Causal Tracing of Indirect Prompt Injection

Indirect prompt injection causes LLM agents to follow commands embedded in external data. A probe may distinguish instructions from data without identifying a state edit that changes the next action. We study this gap through counterfactual role probes, component-wise activation patching, and separate interventions on AgentDojo trajectories. Role decoding survives changes in content and format. In controlled Qwen tests, it precedes strong tool-choice effects from patches along an independently estimated role direction. On AgentDojo, directions estimated from hijacked and resisted training trajectories reduce attack success at pre-action and injected-span positions, but have little effect at random positions. In longer Qwen trajectories, single-position edits become less effective at later layers; span-wide and repeated edits reduce attack success on the same evaluation set. Removing the learned channel subspace preserves role decoding, yet effective intervention directions transfer poorly across the tested channels. These findings distinguish a readable role signal from an effective behavioral intervention: depth matters in controlled tool choice, while position and context also matter in attack trajectories.

Zhe Yu, Wenpeng Xing, Xingxing Yang +1

Zhejiang University · Binjiang Institute of Zhejiang University · Hong Kong Baptist University

Causal Reasoning in Language Models Indirect Prompt Injection Prompt Injection Defense Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents Causal Interventions in Language Models

Sep 30, 2026cs.AI

Inferring Causal Relations between Two Sequences of Events with Language Models

Causal AI is a branch of Artificial Intelligence which helps understand and reason about cause and effect relationships, not just patterns or correlations. Causal discovery aims to infer elements of the underlying causal structure--often represented as a directed graph--from observational and, when available, interventional data. While causal discovery is the fundamental step for moving beyond mere associations toward genuine understanding, and thus the basic building block of causal AI, it becomes intrinsically difficult when causal relations must be inferred from single observations. In such situations, standard causal discovery methods cannot be used and one has to identify causal relations from limited amount of information. This is typically the case for, e.g., sequences of events produced by different alarms which need to be analyzed on the fly to detect abnormal phenomena, which are usually rare. We show in this study that it is possible to leverage the predictive power of Large Language Models (LLMs) to infer causal relations between only two sequences of events. This approach, which is validated on both synthetic and real data, provides better results than standard causal discovery algorithms on several time series data, even though these data were converted into smaller, single observed sequences.

Nishchal Prasad, Eric Gaussier, Emilie Devijver +3

INRIA, Univ. Grenoble Alpes, CNRS, LIG · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG · Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG +1

Time-Series Causal Discovery Causal Discovery Causal Reasoning in Language Models

Sep 28, 2026cs.LG

Small transformers track Bayesian evidence for latent common causes via a context-invariant mechanism

We present an in-depth investigation of how a form of Bayesian reasoning about common causes can emerge as a cross-contextual generalization in small, tractable transformers. Incrementing on recent work, our set-up (i) disentangles causal mechanisms in the model from the causal structure of the true data-generating process, (ii) orients more towards natural language prediction by considering inference of latent common causes, and (iii) considers whether and how Bayesian evidence accumulation for latent common causes can be implemented in representations and mechanisms that allow for cross-context generalization to novel test cases.

Amir Mohammadpour, Michael Franke

Department of Linguistics, University of Tübingen

Bayesian Inference Causal Reasoning in Language Models Causal Inference Causal Interpretability

Sep 9, 2026cs.AI

TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards

Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advantage: establishing the true cause of an anomaly often requires costly expert investigation and may remain ambiguous after the fact. We ask whether this asymmetry of verification can instead be engineered. We sample an intervention, inject it into a controlled simulator, and generate the observations it would produce. The hidden intervention provides an oracle label and objective reward, while the agent must still investigate noisy, confounded, and distributed evidence. We instantiate this approach in TRACE, a digital-advertising diagnostic environment with 12 root causes and fine-grained segment attribution. Agents investigate each episode using Python and SQL and must identify both the root cause and, when applicable, the affected segment assignment. On a held-out 235-episode test set, the strongest prompted baseline, Claude Opus 5, reaches 0.686 FullAttr@1. Supervised fine-tuning raises Qwen3.5-35B-A3B from 0.159 to 0.637, and subsequent RL with synthesized rewards reaches 0.757, outperforming all evaluated prompted baselines, including frontier closed-source models and a prompted Qwen3.5-122B-A10B model. The resulting policy also uses substantially fewer tool calls than the prompted 35B base. These results provide evidence that access to a scalable, objective training signal can be a more important constraint than model scale alone. More broadly, simulation-based verification can make otherwise ambiguous diagnostic reasoning tasks amenable to scalable reinforcement learning.

Rui Sun, Zhan Shi, Bing He

Independent Researchers

RL for Language Model Reasoning Causal Reasoning in Language Models Reinforcement Learning with Verifiable Rewards Root Cause Analysis

Sep 7, 2026cs.AI

CausalVerify: An Execution-Grounded Benchmark for LLM Causal Inference Workflows

Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recovers the target causal estimate. CausalVerify studies this verification problem for structured econometric causal-estimation workflows by separating realistic interpretation from verifiable computation. It pairs 259 published economics papers (reconstructed research question, data description, institutional context) with 100 fixed-seed synthetic scenarios that realise CSV datasets for difference-in-differences, event study, instrumental variables, and regression discontinuity designs. Experiment A (real-paper text agreement) scores method-family and direction agreement against four-LLM consensus labels. Experiment B (synthetic execution) runs model-written R code and checks whether the extracted treatment-effect estimate matches a canonical estimator on the same realised dataset; this execution-grounded correctness layer is L2b+, distinct from L2b, which records only whether the code executes. A calibration arm asks whether self-reported confidence separates correct from incorrect workflows. On Experiment B, seven LLMs reach L2b+ pass rates of 10% to 88% at the default 50% tolerance, and 66 of the 426 workflows that execute (15.5%) return a wrong estimate. Execution ranking (L2b) agrees with L2b+ far better than text-direction scoring (L4): Kendall

τ=0.81

and Spearman

ρ=0.93

, versus Kendall

τ

between

-0.20

and

0.10

for L4. Llama-3.3-70B-Instruct shows the same qualitative gap, and reported confidence does not reliably separate correct from incorrect workflows. The claims are confined to standardized single-shot workflows in these four design families under the evaluated R backend and model panel; the benchmark does not measure general causal-inference ability. Code, data, cached outputs, and a datasheet are released.

Yonghong Zhang, Ricardo Correia, Isabel M. Parra +1

Department of Finance Universidad Autónoma de Madrid Madrid, Spain · Spanish National Research Council (CSIC) Madrid, Spain

LLM Evaluation Causal Effect Estimation Causal Reasoning in Language Models Causal Inference

Sep 3, 2026cs.AI

From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research

Research and news coverage of language-model deception increasingly attributes human-like mental-state concepts to language models. Such claims can blur the distinction between behavior that looks deceptive and a mechanism that is actually deceptive. We introduce a causal taxonomy separating prior commitment from retrospective report, model preference from realized output, false preference from sensitivity to the utility of misleading a recipient, and deceptive behavior from the provenance of the objective or strategy producing it. We test these distinctions in two open-weight model families. Across controlled guessing-game and stock-trading experiments, we find that deceptive-looking behavior can arise without the corresponding proposed mechanism, while other interventions provide direct evidence that recipient information state can causally affect deceptive preference. These results show that deceptive behavior can provide evidence for a deceptive mechanism. But even evidence for such a mechanism does not establish model agency in the deception.

Yakov Pyotr Shkolnikov

Independent Researcher

Deception in Language Models Causal Reasoning in Language Models

Sep 1, 2026cs.LG

CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN

The next generation of mobile networks is envisioned as fully AI-native, with AI-RAN architectures embedding small language models (SLMs) to perform reasoning over real-time telemetry. The state-of-the-art training paradigms for telecom LLMs, exemplified by RANSTRUCT-style supervised fine-tuning (SFT) on curated instruction data, are limited to post hoc rationalization. Here, the explanations, when produced at all, are generated after or independently of the decision, leaving the decision process unauditable. Pre-hoc reasoning, where a causal reasoning trace is produced before the output label, is preferable, and the broader LLM reasoning literature has made real progress toward it via RL methods such as Group Relative Policy Optimization (GRPO). Here we observe that transplanting this recipe into the telecom setting runs into a cold-start barrier: SLMs either learn to output the desired format or learn to predict the label, but rarely both. We identify this barrier and propose CRAFT, which stands for Cold-start Reasoning Alignment via Fine-Tuning, a data-centric method to autonomously generate a verified dataset of (input, trace, label) triplets. CRAFT fine-tunes SLMs on this verified data using low-rank adaptation (LoRA), requiring substantially less compute and wall-clock time than GRPO-based methods. On the TRACTOR and IC xApp telecom datasets, CRAFT achieves up to 86.5% and 94.6% for accuracy and F1 with no parse failures, while direct GRPO and SFT+GRPO fail to exceed 28% and 53.5% F1 with multiple parse failures. We further show that CRAFT-initialized policies serve as a robust foundation for subsequent GRPO fine-tuning, as under diverse reward functions the performance remains consistent with no parse failures. Finally, we demonstrate that CRAFT consumes 59% less energy than GRPO-based baselines, making it a sustainable path to deployable, auditable AI in 6G RAN.

Pranshav Gajjar, Vijay K Shah

NextG Wireless Lab NCSU Raleigh USA

6G Networks LLM Interpretability RL for Language Model Reasoning Causal Reasoning in Language Models LLM Post-Training

Aug 31, 2026cs.LG

Generative artificial intelligence for reliable mechanistic reasoning for corrosion

Corrosion accounts for approximately 4% of global GDP, and reliable prediction is essential for timely mitigation. Machine learning effectively predicts corrosion rates from composition, microstructure, and environmental variables, but cannot explain the underlying mechanisms. A reliable approach in safety-critical materials engineering requires not only accurate retrieval but also mechanistically defensible reasoning, a capability that existing factuality metrics cannot assess. This work presents a domain-adapted retrieval-augmented generation framework for corrosion knowledge synthesis, demonstrated on magnesium alloy corrosion. Three open-weight language models (Llama-3.1-8B, Qwen-2.5-7B, Mistral-7B) are fine-tuned on 3,309 expert-verified question-answer pairs from 840 peer-reviewed papers and integrated with a hybrid dense-lexical retrieval pipeline. Retrieval augmentation produces Token F1 gains of 143-194%, with system faithfulness of 0.964 and context recall of 0.988. Blind external validation on newly published literature and in-house electrochemical data confirms trend-level generalisation. Reason Map, a proposition-graph framework, is further introduced; it independently constructs directed evidence graphs from generated answers and retrieved literature, enabling systematic detection of causal direction inversions and unsupported inferential leaps that flat factuality metrics cannot expose. The modular architecture can be applied across domains, offering a generalizable blueprint for trustworthy AI-assisted knowledge synthesis to circumvent corrosion, which can also be applied to other engineering domains.

Bharath M N, R K Singh Raman, Alankar Alankar

Department of Mechanical Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, 400076, India · Department of Mechanical and Aerospace Engineering, Monash University, Clayton 3800, Victoria, Australia · IITB-Monash Research Academy, Mumbai, Maharashtra, 400076, India +1

Retrieval-Augmented Generation Causal Reasoning in Language Models Materials Science Evidence-Grounded Generation

Aug 12, 2026cs.CL

Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library

When a language model answers an interventional question, the computation it must perform depends on the type of evidence the query requires. We report a decoupling in how a transformer organizes causal knowledge: slot-by-type structure induced by type-level supervision organizes routing, yet remains functionally decoupled from answer readout. We establish this with a typed mechanism library -- discrete mechanism slots partitioned by evidence type, auditable at the state level -- on a causal-world benchmark with exact interventional ground truth, under a frozen protocol, at two scales (22.6M and 125M). Four preregistered findings. (i) Origin. Slot-by-type organization is induced by type-level supervision: absent in architecturally identical unsupervised controls, not buyable by content-free gating labels, and statistically attributable to the supervision signal, replicating at 125M under a powered preregistered protocol (all nine cells passed). (ii) Boundary. The induced structure is a typed routing index with a sharp routing/readout boundary: slot codes scaffold routing but do not drive answer readout (

|Δ\hat{y}| \le 3.4\times10^{-6}

, zero collateral, three seeds, stable across a 5.6x scale window) -- we therefore make no behavioral-editability claim. (iii) Cost. The structure is free: LM quality matches a parameter-matched monolith within 0.0082 nats. (iv) Trust. The library state is exactly local under edit and bit-exactly revertible -- 250 single-edit and 1,000 stacked reverts per seed, zero failures. We further find that the unsupervised null itself moves with scale, so comparisons reusing a null calibrated at one scale may be confounded at another. Every claim is tied to a preregistered, machine-checkable criterion archived before the data it governs; the full audit trail, including one criterion we failed and how the frozen protocol handled it, is released as an appendix.

Xining Xun

Tsingjiao Information Science (Beijing) Co., Ltd.

Causal Representation Learning LLM Auditing Causal Reasoning in Language Models LLM Routing Causal Interpretability

Aug 4, 2026cs.LG

DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs

Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarce, records rarely contain reasoning paths, and data transfer poorly across configurations, complicating local deployment. We present DiagLoop, a counterfactual data flywheel that converts codified physical relations or clinical guidelines, authored once per mechanism family, into training supervision beyond recorded cases. A training-only teacher proposes counterfactual worlds by varying causes, contexts, and observations, while an independent hybrid checker admits only valid worlds. The student reasons through symptom abstraction, causal-chain construction, and root-cause attribution. Stage-specific criteria identify its earliest failure. For nonterminal failures, a bounded repair probes downstream competence, and the resulting weakness profile guides subsequent data generation. Stage-localized reinforcement learning updates only the model-generated continuation, while replay and preservation reduce forgetting. The same criteria govern admission, attribution, reward, and regeneration through checks separate from the proposer. Using only synthesized scenarios and no case-level expert reasoning annotations, the resulting 8B model improves strict path correctness over the strongest conventional baseline. Gains are 11.6 points across eight industrial systems and 5.5 points across ten disease categories. Gains over a deranged-routing control are 3.9 and 2.3 points, respectively. The model also exceeds the evaluated proprietary references in both domains, even when they receive few-shot examples or the specification in context.

Jian Zhang, Bingyi Wang, Yizhi Liu

Zhejiang University

RL for Language Model Reasoning Causal Reasoning in Language Models Clinical Reasoning Counterfactual Data Augmentation Fault Diagnosis

Aug 4, 2026cs.LG

CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning

Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning. Although large language models perform well on such tasks, privacy, latency, and controllability motivate distillation into locally deployable models. Standard trajectory imitation does not correct process errors on the student's own rollout distribution. We propose CausalOPD, a curriculum online process distillation framework. A knowledge-augmented teacher first provides trajectories grounded in domain-specific causal rules, entity relations, and structural constraints. The student then generates on-policy trajectories, and the teacher identifies the first wrong step, defined as the earliest transition that verifiably violates available constraints. Starting from the verified prefix, short-horizon reinforcement learning repairs this localized failure. A causal-stage curriculum advances from evidence-level to mechanism-level and conclusion-level errors, following their propagation order. Across three domains, CausalOPD improves average path correctness by 23.4 percentage points over sequence-level online process distillation and reduces the right-label-wrong-reasoning rate from 15.7% to 4.4%. The domain-specific 8B students also surpass both evaluated proprietary references in path correctness across all domains.

Jian Zhang, Bingyi Wang, Yizhi Liu

Zhejiang University

Curriculum RL Causal Reasoning in Language Models Process Supervision Causal Reasoning On-Policy Distillation

Aug 4, 2026cs.AI

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer. On CLEAR find-one-valid queries that admit multiple graph-valid answers, CALVER reaches 42.1% where plurality, a reward model, an LLM judge, and model confidence remain near 30% on identical frozen pools. Scaling the judge to 72B does not close the gap. In an audited clean-core subset, 11 of 21 graph-valid CALVER selections differ from the benchmark's listed answer while still satisfying the requested predicate. The advantage widens with the sampling budget and reproduces across ten published Bayesian networks, a second model family, and settings where the model must build the graph from text. CALVER also improves thresholded average-treatment-effect decisions against exact ground truth, generalizes to logic under a truth-table checker, and scores each candidate in milliseconds on CPU. CALVER needs only a causal structure, supplied outright or built from the text; wherever that holds, selection can aggregate via causal validity.

Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague +2

The University of Texas at Austin · New York University

Self-Consistency Decoding Symbolic Reasoning Causal Reasoning in Language Models Causal Inference

Jul 31, 2026cs.CL

Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?

Interventional data is widely regarded as the gold standard for teaching models causal reasoning. We test this assumption in a fully controlled synthetic environment pitting observational correlation against causal effect, and find it fails instructively. In Simpson's-paradox worlds, where the two have systematically opposite signs, increasing the fraction of interventional samples in pretraining does not improve causal direction: the magnitude of the model's do()-response grows monotonically, yet its sign is copied from the observational context. What governs whether interventional evidence is used is not the training mixture but the evidence type present in the context at inference time. Under an identical training recipe, a purely observational context induces systematic sign reversal in 29/50 worlds, a mixed context in 19/50, while aligned interventional probes alone yield 41/50 correct. Erasing observational evidence from the context immediately releases the suppressed causal interpolation ability (ratio_true = +0.56); a four-state content manipulation shows the switch is content-mediated and graded. The suppression is stable across training seeds (11/11 strong reversals persist on a matched-protocol second seed) and robust as a rate at 0.93B parameters (31.8% vs. 6% reversals in the matched probe-only arm), even as absolute gains shrink four-fold. An external audit on CLadder exposes a learned positive-effect prior with a two-layer structure: sign-randomized retraining removes it in-distribution but not out-of-distribution. We summarize: the capability lives in the weights; the switch lives in the context, and activation patching localizes the switch to the middle layers' observational rows. We further quantify the sampling noise floor of probe-based causal evaluation and an evidence-averaging protocol that cuts sign errors from 26% to 9%.

Xining Xun

Tsingjiao Information Science (Beijing) Co., Ltd.

Causal Discovery Causal Reasoning in Language Models Causal Interpretability Causal Interventions in Language Models

Jul 29, 2026cs.CL

Same Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model States

The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes, estimands, pathways, or identifying assumptions. When the evidence and target vary together, a correct answer may reflect favorable or adverse wording, lexical overlap, or a familiar diagnostic pattern rather than matching the evidence to the causal question. We introduce paired prompts that repeat the same diagnostic evidence verbatim while changing the causal target. Each prompt is labeled Favors, Challenges, Unresolved, or Wrong Target according to how the evidence bears on the causal question. A pair is recovered only when both prompts are classified correctly. Using linear readouts trained on a separate development set, we analyze the final-token hidden state from the penultimate transformer block of Qwen2.5-7B-Instruct, Qwen3-8B, and Llama-3.1-8B-Instruct. On the 49-pair primary benchmark spanning nine diagnostic families, balanced accuracy ranges from 0.654 to 0.659 and 18-21 pairs are recovered. Two independent human reviewers assigned the same label to 95 of the 98 prompts (96.9%). Across checkpoints, balanced accuracy and complete-pair recovery exceed permutation nulls that preserve development scenario groups. In Qwen2.5, full-prompt balanced accuracy exceeds both restricted inputs, with paired-bootstrap intervals for both differences above zero. Readouts trained without development examples from the evaluated diagnostic family recover 21 pairs, including at least one in each of the nine families. The hidden-state readout exceeds a linear classifier on answer-option logits and text baselines in balanced accuracy and recovered pairs. These results show that the hidden state contains linearly decodable information about whether diagnostic evidence favors, challenges, or fails to address the causal target.

Weiyi Kong, Zhuoran Li

University of Toronto, Toronto, Canada · The University of Hong Kong, Hong Kong

Causal Reasoning in Language Models Causal Inference Causal Interpretability

Jul 23, 2026cs.LG

Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA

Bridge infrastructure deteriorates gradually, yet its root causes---salt intrusion, freezing, fatigue cracking, and others---remain invisible to the naked eye. Expert diagnosis relies on tacit knowledge built over years of practice. We address the challenge of automating this latent causal reasoning by proposing a Damage Cause Encoder that classifies 10-class damage causes from visible damage descriptions

S_i

for use in autonomous bridge diagnostic agents. Our approach chains three components: (i)Knowledge Triple Extraction---a large language model extracts causal triples of the form (damage

\xrightarrow{\mathtt{caused\_by}}

cause) from 15--35 diagnostic PDF manuals and indexes them in a FAISS vector store; (ii)Retrieval-Augmented Context---at training and inference time, relevant causal triples

\mathcal{C}_i

are retrieved and concatenated with

S_i

, converting implicit domain knowledge into explicit Encoder context; (iii)Systematic Fine-tuning Comparison---we conduct a rigorous comparison of LoRA, QLoRA, and QA-LoRA on a fixed Golden Testset (116 stratified samples), demonstrating that QLoRA achieves the optimal trade-off: identical test accuracy (87.07%) to full-precision LoRA, 11% faster inference, 72% lower GPU memory, and superior generalization across diverse unseen inputs. A controlled Golden Testset---stratified, deduplicated, and difficulty-tagged---is introduced as a reusable benchmark contribution. QLoRA further outperforms LoRA by 13 percentage points on a 100-sample diverse evaluation spanning all 10 damage cause classes.These findings enable memory-efficient, high-accuracy diagnostic agents on consumer-grade hardware for edge deployment.

Takato Yasuno

Causal Attribution Low-Rank Adaptation Causal Reasoning in Language Models Quantization-Aware LoRA Structural Health Monitoring

Jul 21, 2026cs.CL

CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness

Chain-of-thought (CoT) reasoning is widely used to improve both the performance and interpretability of large language models (LLMs), yet the generated reasoning may not faithfully support the final answer. We study this problem from a causal perspective, where a faithful CoT process should follow the chain

Z\rightarrow X\rightarrow Y

, with

Z

,

X

, and

Y

denoting the instruction, reasoning chain, and final answer, respectively. In this process, the instruction should affect the answer only through the reasoning chain. However, conventional autoregressive LLMs condition answer generation on both the instruction and the CoT, which still allows a direct instruction-to-answer shortcut. To address this issue, we propose CASE, a framework that combines training-time causal alignment and inference-time structural enforcement. During training, CASE builds counterfactual-CoT, biased-instruction, and empty-instruction datasets, and applies selective-loss fine-tuning to strengthen CoT-to-answer dependence while suppressing instruction shortcuts. During inference, CASE masks direct attention from instruction tokens to answer tokens, preventing the model from bypassing the generated CoT. We provide an information-theoretic analysis showing how these components promote faithful chains. Experiments on three models and four benchmarks show that CASE achieves a 37% average per-setting relative improvement in overall CoT faithfulness over the strongest baselines, exhibits stronger cross-dataset faithfulness transfer, and maintains competitive average accuracy. Code is available at https://github.com/oddwang/CASE.

Ziming Wang, Yinghua Yao, Changwu Huang +2

Department of Computer Science and Engineering of Southern University of Science and Technology, Shenzhen, China · Center for Frontier AI Research, Agency for Science, Technology and Research (A*STAR), Singapore · School of AI and Liberal Arts, Beijing Normal-Hong Kong Baptist University, Zhuhai, China +1

CoT Faithfulness Faithfulness of Language Model Explanations Causal Reasoning in Language Models Causal Interventions in Language Models LLM Reasoning

Jul 21, 2026cs.LG

PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects

Evaluating machine learning in scientific domains requires separating correct predictions from correct reasons under realistic distribution shifts. We introduce PertReason, a knowledge-grounded benchmark and framework suite for cell-state--conditioned reasoning about perturbation effects. At its core, PertReasonQA is a benchmark that tests whether models can generate mechanistically faithful explanations while remaining robust to complex shifts, such as new cells and unseen perturbations. PertReasonQA combines single-cell genetic and chemical perturbation data across multiple cellular contexts with knowledge graphs, and dynamically conditions pathways on cell-specific basal states to avoid generic memorization. Evaluations on state-of-the-art models reveal systematic gaps between predictive accuracy and mechanistic reasoning. Specifically, these models exhibit failure modes largely invisible to standard benchmarks, such as deriving correct answers through flawed logic, ignoring cellular context, and generating directionally inconsistent mechanisms. As a reference probe of the benchmark, we present PertReasonLM, a large language model trained to align outcome predictions with context-specific mechanistic reasoning. Our model targets the identified failure modes by grounding rationales in context-specific pathways and tightening agreement between outcomes and mechanisms. Together, we provide a diagnostic framework for exposing and mitigating failures in faithful reasoning in data-rich scientific systems.

Dongkwan Kim, Yiming Gao, Yining Yang +1

Department of Electrical and Computer Engineering, Texas A&M University

LLM Grounding Single-Cell Perturbation Modeling Causal Reasoning in Language Models Large Language Model-Guided Scientific Discovery

Jul 20, 2026cs.CL

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

Discourse relations provide document structure, critical to language understanding and enabling language model performance and ethicality. In this work, we investigate how instruction-tuned Transformer models (LLaMA and Mistral) encode discourse relations in English, with a particular focus on the contrasting relations of causation and antithesis. Framing the task as a next-token prediction task and applying a suite of interpretability techniques to test model internals, our findings show that certain early layers make predictive decisions at mid-sequence tokens, while some mid-level layers finalize their decisions closer to the last token. Most of the remaining layers primarily propagate earlier decisions rather than actively influencing them. Additionally, we observe that some layers exhibit a preference for one answer over alternatives, suggesting asymmetric representation of discourse-based reasoning.\footnote{Our code is available at https://github.com/abhidipbhattacharyya/causation_vs_antithesis}

Abhidip Bhattacharyya, Shira Wein

University of Massachusetts Amherst · University of South Florida

Transformer Interpretability Causal Reasoning in Language Models

Jul 19, 2026cs.AI

An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning Evaluation

Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance: hallucination, frozen knowledge, poor explainability, and poor modifiability. This paper proposes data-first ontology: LLMs are treated as reasoning and language engines, while deterministic knowledge is moved into an explicit multimodal database, DaoQL. We formalize an explicit world model and show that, under rule independence, deterministic evaluation, and fixed conflict resolution, explicit models provide a sufficient condition for composable counterfactual decomposability; implicit models lack atomic read/delta semantics and therefore provide no comparable architectural guarantee. The implemented system focuses on DaoQL's verified storage layer and explicit Eval path, integrating graph, column, vector, and full-text engines within one process. KVCache graph nodes, expert hot updates, and the DaoQL-Agent runtime remain future work. On an embedded same-machine setup, DaoQL reports graph BFS at 1.20 ms, HNSW at 83.1 us, and a Fluent hybrid query at 105.8 us; these results indicate engineering potential but must be interpreted with deployment-shape differences from client-server systems. Exploratory measurements on LDBC SNB SF1 and ANN-Benchmarks further show 34/34 query coverage with interactive-class queries mostly in the sub-millisecond to millisecond range, but only 1.8 QPS overall due to long-tail BI/IC queries; ANN-Benchmarks reaches Recall@10 >= 99% at thousand-level QPS after a bridge-edge protection fix. In a five-domain counterfactual experiment (n = 1250), DaoQL+GPT-4o achieves 94% composable counterfactual decomposability, 49 percentage points above GPT-4o alone. The paper explicitly separates provable structure, preliminary empirical evidence, and architectural roadmap claims.

Zhanbo Li, Shifeng Wu, Xiangjin Meng +1

Graduate Students, School of Mathematics and Statistics, Chongqing University · DaoQL Project Group · Guangzhou Polytechnic Normal University

LLM Grounding Counterfactual Reasoning in Language Models Causal Reasoning in Language Models LLM Reliability Counterfactual Reasoning

Jul 16, 2026cs.CV

WorkDrive: Roadwork Chain of Causation for Autonomous Driving

Autonomous driving vision-language models (VLMs) struggle in roadwork zones, where familiar visual cues such as lane markings and permanent signs are altered or absent, and temporary devices such as cones and barriers redefine the drivable corridor. VLMs can detect these objects, but without explicit guidance they anchor their reasoning on familiar elements from pre-training and fail to connect work-zone observations to correct planning decisions. We propose WorkDrive, a framework that constructs perception-grounded causal reasoning for work zones and aligns it with trajectory prediction. An automated multitask perception pipeline extracts structured scene facts and injects them into a Chain-of-Causation (CoC) annotation pipeline, redirecting the annotator's attention to domain-specific elements. The resulting reasoning labels are used for supervised fine-tuning, followed by reinforcement learning with a single reward: consistency between lateral meta-actions and the predicted trajectory. On ROADWork, the largest public work-zone dataset, the proposed roadwork CoC reduces trajectory average displacement error (ADE) by 9.0%, and consistency-based GRPO yields a further 3.0%, achieving progressive improvement over the trajectory-only baseline. Code and data will be publicly released.

Tianyi Jiang, Wen Zhang, Sihan Yang +2

Peking University · Beijing, China · Xiaomi EV

VLMs for Autonomous Driving Autonomous Driving Perception Causal Reasoning in Language Models Vehicle Trajectory Prediction

Jul 15, 2026cs.CL

Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis

Systematic comparisons between current situations and structurally similar past events in the historical, i.e., historical analogies, is among the most powerful tools for foresight analysis. In this work, we present a new task called Analogical Deep Research (ADR) to Large Language Model (LLM) agents and construct the first ADR benchmark ADR-bench to study whether LLM agents are able to find and leverage historical analogies when doing foresight analysis. Our investigation reveals a key obstacle: LLM agents are poor at finding analogies because they match on surface features rather than underlying mechanisms. We argue that ADR is inherently a causal question as it requires understanding why the event occurred. Based on our theoretical analysis, we propose two principles required for ADR, including the mechanism alignment and cross-analogy confirmation. Built upon our theoretical results, we propose a new agentic framework called Causal Analogical Researcher (CANA) that guides LLMs to find and integrate historical analogies. CANA incorporates a simple yet effective structural decomposition representation, and integrates structural feedback for reflective improvements of historical analogy identification and integration. We show that CANA brings up to 10% improvements in historical analogy generation, and surpasses the state-of-the-art deep research agents in the ADR-bench. Case studies with the ongoing events confirm the effectiveness of CANA in leveraging historical analogies.

Yongqiang Chen, Guangyi Chen, Yuewen Sun +1

1Mohamed bin Zayed University of Artificial Intelligence · 2Carnegie Mellon University

Analogical Reasoning LLM Agent Evaluation Causal Reasoning in Language Models Autonomous Research Agents

Jul 9, 2026cs.AI

CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure. Furthermore, existing causal evaluation datasets are often restricted to curated examples from existing sources, with diversity coming from limited templatized variations rather than from systematic generation of novel synthetic causal structures. We introduce CausalDS, a benchmark for evaluating causal reasoning in agentic data-science workflows. Each benchmark instance is a scene consisting of a sampled structural causal model (SCM) with generated observational data and an accompanying synthetic natural-language story grounded in a realistic domain. We optionally ground the composition of the benchmark components in empirical distributions obtained from real-world datasets, thus retaining empirical structure while reducing the "causal parrot" risk through completely synthetic generation. From each scene, we then derive tasks spanning all three of Pearl's rungs, with typical data-science prediction tasks appearing as Rung 1. Most tasks include a data science coding component, where the model typically needs to use several tools to arrive at the final answer due to the frequent presence of imperfect observations, which are generated by an observation model. Additionally, recognizing when a question admits no warranted answer and abstaining is treated as a first-class scored outcome. The benchmark thus jointly evaluates symbolic causal reasoning, data science, uncertainty quantification, abstention, and tool use/coding.

Andrej Leban, Yuekai Sun

Department of Statistics University of Michigan Ann Arbor, MI, United States

Structural Causal Models AI Agent Benchmarks Causal Reasoning in Language Models Synthetic Benchmark Generation Causal Reasoning Data Analysis Agents

Jul 5, 2026cs.CL

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention. Since scientific discovery fundamentally relies on uncovering causal relationships from observations, the capability of causal thinking, i.e., distinguishing causation from correlation and recognizing hidden biases, is essential to LLM agents. Although a number of benchmarks exist for AI Scientists, none explicitly incorporate challenges from selection bias, measurement error, and hidden confounders that widely exist in real-world scientific discovery. To this end, we present CausalGame, a benchmark that evaluates the causal thinking capabilities of LLM agents through interactive games. CausalGame asks LLM agents to actively design experimental protocols, collect observation data, and derive a final solution with an explanation report. To emulate realistic scientific discovery challenges, we design 14 scenarios that incorporate selection bias, measurement error, and hidden confounders. Across 30 LLM agents, none demonstrates reliable causal thinking: the best model reaches only 68.0% survival against analytical optima of 78-85%, and merely 5-7% of sessions receive credits on the causal-reasoning rubrics. CausalGame provides a scalable and controlled testbed for evaluating the causal thinking of AI Scientist agents.

Zhenhao Chen, Yongqiang Chen, Chenxi Liu +7

1MBZUAI · 2Carnegie Mellon University · 3TMLR Group, Hong Kong Baptist University +2

AI Agents for Scientific Discovery AI Agent Benchmarks Causal Reasoning in Language Models Causal Reasoning

Jun 25, 2026cs.AI

OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, existing datasets suffer from a fundamental gap: they label only the root cause, not the propagation path connecting it to the observed symptom, which largely simplifies the task to naive pattern matching. To support rigorous evaluation, we introduce PAVE, a step-wise labeling protocol that leverages known interventions from fault injection to reconstruct causal propagation paths. The mechanism is forward verification: reasoning from cause to effect rather than inferring backward from symptoms. Applying PAVE yields OpenRCA 2.0 (500 instances), the first cross-system RCA benchmark with step-wise causal annotations for LLM agents. Across 11 frontier LLMs, recovering the exact root-cause set succeeds in only 20.7% of cases on average. To locate where this difficulty lies, we relax the criterion and find what we call the ungrounded diagnosis: agents identify at least one correct root-cause service in 76.0% of cases, but ground that service in a verified causal propagation path to the observed symptom in only 61.5%. Outcome-only evaluation hides this failure mode; step-wise causal ground truth is the missing piece for trustworthy LLM-based RCA agents.

Aoyang Fang, Yifan Yang, Jin'ao Shang +7

The Chinese University of Hong Kong, Shenzhen · Lero · The Chinese University of Hong Kong

LLM Agent Evaluation Causal Attribution AI Agent Benchmarks Causal Reasoning in Language Models Process Supervision Root Cause Analysis

Jun 23, 2026cs.AI

When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs

Large language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior benchmark studies have primarily evaluated LLMs' causal reasoning capabilities, a more fundamental epistemic dimension has been overlooked: Causal Caution, defined as the propensity to refrain from causal judgment when empirical evidence is insufficient. This study examines the systematic suppression of Causal Caution that occurs when LLMs shift from academic to practical advisory contexts. Using an evaluation rubric inspired by Pearl's Causal Hierarchy (the PCH score), we conducted experiments on four high-performance LLMs -- Claude Sonnet 4.6, Claude Opus 4.7, GPT 5.5, and Gemini 3.1 Pro -- across 480 trials. Causal Caution maintenance rates were 91.7--100.0% in academic contexts but dropped to 6.7--18.3% in practical advisory contexts (Fisher's exact test, p < .001 across all models). Furthermore, when restricted to practical prompts requesting concrete recommendations or explanatory rationales, only 1 of 200 responses (0.5%) maintained Causal Caution. A brief self-correction prompt -- "Please reconsider this judgment from the perspective of causal relationships" -- restored the expression of Causal Caution to maintenance rates of 71.4--100.0% (McNemar's test, p < .001 across all models). These results suggest that helpfulness-oriented response patterns may suppress the expression of Causal Caution in practical advisory contexts, with important implications for organizational governance. The findings indicate that this suppression reflects context-dependent variation in expression rather than an underlying capability limitation, suggesting that multi-agent architectures that separate proposal generation from causal auditing may offer a promising governance design.

Hiroshi Okumura

Mitsubishi Research Institute, Inc. · Kobe University

LLM Auditing Pragmatic Reasoning in Language Models Causal Reasoning in Language Models

Jun 21, 2026cs.CL

Words as Difference Makers: How Large Language Models Determine Causal Structure in Text

Because large language models (LLMs) are impressively successful in predicting text, it appears that they must have access to a 'world model' representing causal and definitional structure. However, the dominant formalisms of modern causal inference -- Judea Pearl's interventionist approach and the Neyman-Rubin potential outcomes framework -- struggle to illuminate how LLMs learn causal structure. I resolve this puzzle by arguing that LLMs employ a specific inductive approach based on a difference-making logic -- sometimes called variational induction. I demonstrate how central aspects of this logic are realized during training, where LLMs require enormous amounts of text data from a wide range of contexts to identify difference- and indifference-makers within word sequences. Furthermore, I analyze specific architectural features of LLMs -- such as token embeddings and self-attention -- to determine their roles in variational induction. The difference-making logic of LLMs fundamentally parallels the experimental method, where causal relations are derived by systematically varying individual circumstances to determine their influence on a phenomenon.

Wolfgang Pietsch

tum

Causal World Models LLM Interpretability Causal Structure Learning Causal Reasoning in Language Models LLM Training

Jun 21, 2026cs.AI

ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery

Generative models have revolutionized the process of materials discovery, yet they often fail to satisfy underlying physical causality. Through an analysis of Large Language Models (LLMs) augmented with knowledge graphs derived from current literature, we uncover a phenomenon termed contextual tunneling, where models "over-anchor" on narrow, retrieved evidence while suppressing global physical reasoning. To address this problem, we introduce ARIA, a causal-aware framework that conditions knowledge use on mechanistic completeness. ARIA routes each query through a three-tier cascade: (i) direct causal reasoning when complete evidence chains of Process-Structure-Property (PSP) are available, (ii) physics-informed analogical transfer for sparse or novel material systems, and (iii) explicit parametric fallback when external evidence is incomplete. As a proof of concept, we construct a Knowledge Graph (KG) containing 2,839 extracted PSP relations from peer-reviewed articles in the materials literature and evaluate ARIA on forward prediction and inverse design tasks for two-dimensional (2D) materials. ARIA mitigates contextual tunneling, improves over unaugmented and naive KG-augmented baselines, and provides further gains when an online literature search is used for evidence enrichment. Crucially, ARIA produces auditable causal traces, enabling physically grounded and trustworthy AI-assisted materials discovery.

Yi Cao, Liaoyaqi Wang, Jieneng Chen +3

Knowledge Augmentation for Language Models Materials Property Prediction Causal Reasoning in Language Models Materials Science Large Language Model-Guided Scientific Discovery Inverse Design

Jun 20, 2026cs.LG

Local Causal Attribution of Chain-of-Thought Reasoning

Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In this work, we take a local approach toward this goal by analyzing the causal relationships among individual components, termed units, of a given, specific chain-of-thought trace. We construct a structural causal model on these units and relate each unit to the log probability of generating (subsequent) output units. Our algorithm, termed AttriCoT, is a black-box method that performs attribution by estimating importance parameters in the structural causal model using

O(U)

forward passes through the model, where

U

is the number of units. Evaluation of perturbation curves across 5 datasets and 4 reasoning models shows that AttriCoT produces attributions that are more faithful to the model's behavior than alternative methods. The attribution results also reveal notable differences in thought structure between models and domains.

Dennis Wei, Yannis Belkhiter, Erik Miehling +1

1IBM Research.

LLM Interpretability Causal Attribution Causal Reasoning in Language Models Causal Interpretability Reasoning Trace Analysis

Jun 14, 2026cs.CL

Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning

Instruction-tuned language models can answer the same causal-reasoning question differently after its English variable names are replaced by type-preserving placeholders, although the structural causal model and the gold answer are unchanged. We ask whether this lexical gap reflects information loss in the placeholder view or a misaligned read-out from a representation that still carries answer-relevant content. Vernier uses a paired-view weight update as an instrument and then inspects the mechanism left after the gap closes. In the working regimes, the evidence favours representational misalignment. A variable-name probe becomes more accurate on the placeholder view, and activation patching on Qwen-7B, Qwen-14B, and Llama-3.1-8B shows that the decision-token representation can transfer answer identity between views. The update that realigns the views is counterfactual augmentation over original and placeholder prompts, while the answer-subspace KL mainly sharpens intermediate answer-belief agreement. Success is bounded by model family, scale, and task. CRASS transfer is reliable across Qwen scales and Llama, e-CARE remains weak, and preliminary non-causal rename tasks show a similar qualitative pattern.

Zhenyu Yu

College of Computer Science and Artificial Intelligence Fudan University

LLM Interpretability Causal Reasoning in Language Models Causal Interventions in Language Models

Jun 11, 2026cs.AI

Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning

When large language models (LLMs) fail to generalize or make content-sensitive errors in reasoning, it is often taken as evidence that LLMs are not truly reasoning, but rather performing a kind of pattern matching. The implication is that human behavior does not exhibit the same types of failures because human reasoning relies on principled and content-invariant world models. We test this assumption by first evaluating humans and LLMs on their ability to engage in common-sense reasoning about a variety of everyday situations. Our results reveal convergent patterns of reasoning across 46 LLMs and two cohorts of human participants. We then ask whether this behavioral convergence is due to LLMs having acquired content-invariant world models or a set of pattern-matching heuristics by characterizing the roles of content-invariant and content-sensitive model neurons in producing human-like responses. We find that while LLMs encode both content-invariant and content-sensitive representations, it is content-sensitive mechanisms which are causally responsible for aligning models with humans. Taken together, our results suggest that everyday causal reasoning in people and LLMs makes heavy use of pattern-matching.

Zach Studdiford, Gary Lupyan

University of Wisconsin–Madison Department of Psychology Department of Computer Science

Cognitive Modeling LLM Interpretability Causal Reasoning in Language Models LLM Reasoning