Natural Language Inference

Also known as NLI

Ask about this topic

Overview

Natural language inference (NLI) asks whether one text entails, contradicts, or leaves undetermined a claim in another, supporting tasks such as fact checking, argument analysis, and document review. Common approaches fine-tune transformer models or prompt large language models, while linguistic features, semantic graphs, and neuro-symbolic methods aim to make the reasoning more structured and interpretable. Benchmarks range from general-purpose datasets to adversarial, multilingual, clinical, and legal settings, with diagnostics probing phenomena such as negation, lexical changes, and implicit premises. A central challenge is that high benchmark scores can coexist with reliance on dataset artifacts, sensitivity to wording, and gaps between model judgments and human interpretations; annotation ambiguity and benchmark quality also complicate evaluation.

Latest papers

CardsList

40 papers4 papers in the last four weeks, down 60% on the four weeks before. 0.0% of all new papers.

Nov 2, 2026

An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification

Claim verification is the task of deciding whether a source text supports a claim, contradicts it, or lacks sufficient evidence. Natural Language Inference (NLI) models can judge whether a single sentence supports or contradicts a claim, but they struggle when the evidence is spread across several sentences. Conversely, Large Language Models (LLMs) can reason across sentences, but may draw conclusions the text does not support. In this experimental study, we test whether a conservative fusion rule, labeling a claim Support or Contradict only when both models agree and defaulting to Not Enough Evidence otherwise, combines their strengths. We construct a benchmark of 2,035 claims from SciFact and CliniFact (858 Support, 152 Contradict, 1,025 Not Enough Evidence). We retrieve the top five most relevant sentences per claim using a hybrid of semantic and lexical (BM25) retrieval, which slightly outperforms either method alone. These retrieved sentences are then provided to every verification model. We then compare a DeBERTa-v3-base-mnli-fever-anli NLI baseline against Llama 3.1 8B, Qwen3 8B, and Mistral 7B. Qwen3 achieves the highest Macro-F1 (0.7937), followed by Llama 3.1 (0.7204) and Mistral (0.6388), while the NLI baseline reaches only 0.3157. Contrary to our hypothesis, fusion degrades performance, dropping Macro-F1 to 0.7392, 0.6730, and 0.5991, respectively. To understand this decline, we analyze agreements, disagreements, and common error patterns between the NLI and LLM verifiers. Our error analysis shows that NLI and LLM disagreements often result in correct LLM predictions being overturned.

Lakshmi Narayanan P, Narenkarthik K, Naren Kumar C

Shiv Nadar University Chennai, Chennai, India

Scientific Claim VerificationLLM EvaluationNatural Language Inference
AskPDF
Nov 1, 2026

FOLLIE: Automated Reasoning over the First Dataset of Sentences with their First-Order Logical Representation for French

FOLLIE (for First-Order Logic for Language Inference and Entailment for French) connects French sentences, compositional first-order representations and automated natural language inference (NLI). The first French NLI-ready, NL-to-FOL resource, it contains 19,983 inference records and 36,987 non-empty sentence-slot--formula mappings from six heterogeneous NLI sources, retaining French lexical material and source problem structure. Its silver annotations are produced by a neural--symbolic pipeline, with 111 separately identified LLM-assisted additions. The construction combines morphosyntactic analysis, probability-conditioned categorial multitagging, grammatical proof search, discourse representation and first-order semantic construction. Stage-wise experiments show substantial gains in derivation coverage; analyses of conjunction distributions, logical-operator incidence and scope alternation characterise the resulting resource. We then develop an automatic inference engine whose input-conditioned background theories address lexical relations, quantification, quantities, event structure and temporal dependencies. Prover9 supplies proofs for entailment and contradiction, while Mace4 supports bounded consistency checks. Three-way accuracies are 65.37% on all 335 FraCaS-FR problems, 70.33% on 300 GQNLI-FR problems and 71.35% on 9,399 eligible SICK-FR records pooled across splits. Agreement with reference labels among committed decisions is 93.53%, 100.00% and 98.66%, at commitment coverage of 41.49%, 37.00% and 15.05%, respectively. Worked constructions, axiom schemas and proof analyses explain these outcomes and identify the contributions of scope, reference, lexical knowledge and numerical structure. FOLLIE provides a French experimental basis for studying the representations and assumptions that connect sentence interpretation to deductive inference.

Maximos Skandalis

LIRMM, CNRS & University of Montpellier, Montpellier, France

First-Order LogicNatural Language InferenceLogical ReasoningSemantic Parsing
AskPDF
Oct 31, 2026

Dual-Axis Policy Entailment: A Benchmark for Policy-Change Reasoning

Whether a policy shifts domains and, by extension, continues, broadens, narrows, or reverses previous policy is of paramount importance to the study of public policy. We propose Dual-Axis Policy Entailment (DAPE), which evaluates an ordered pair of policy directives on both dimensions at once: a binary judgment determines whether the two directives govern the same policy domain, and a five-way judgment determines whether the later directive continues, broadens, narrows, or reverses the earlier policy, or governs a different domain altogether. Read together, the two judgments form one five-category label, our primary metric. The two-axis design captures two central dimensions of policy change without conflating errors on either dimension into a generic "irrelevant" label, and it makes annotation more rigorous: a coder cannot dismiss a difficult pair as domain-irrelevant without an explicit, checkable decision. We introduce an expert-annotated benchmark of 1,000 ordered directive pairs drawn from a large corpus of Chinese government policy, together with an annotation-calibration protocol (an adjudication packet with pre/post agreement measurement) that we contribute as a methodological artifact. Fourteen open-weight models and four frontier API flagships fail the task zero-shot: even the best frontier flagship's chance-corrected agreement with expert labels is far below the human ceiling (Cohen's κ≈0.29κ\approx 0.29 vs. 0.530.53). A fine-tuned open-weight model (LoRA SFT of Qwen3-14B, five-fold cross-validation) closes this gap, reaching the coder-mutual human ceiling (κ=0.524κ= 0.524 vs. 0.5270.527). Finally, we apply our method to China's AI policy (1980-2024) and map the direction of policy change across eras.

Charles Chang, Yuen Yuen Ang, Bolun Sun

Duke Kunshan University · Johns Hopkins University · Northwestern University

Policy EvaluationLanguage Model Reasoning EvaluationNatural Language Inference
AskPDF
Oct 15, 2026

Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but we do not know what extra thinking does to such everyday inferences. We study this directly: we keep a model's weights fixed, change only how much it thinks, and record which reading it chooses. A second tool cuts the model's own reasoning at successive points and asks for an answer, showing where the reading changes. Thinking makes models read logical words as logic: it cancels the implicatures of some (not all) and or (not both) in most tested open reasoning models and in GPT-5, while context-driven inferences such as indirect answers improve. The trace shows why: models first entertain the enriched reading and cancel it later. Answering from that early reading, an exploratory inference-time remedy, recovers these implicatures without losing literal accuracy. Evaluations of reasoning models should measure how they interpret, not only how accurate they are.

Zhizhuo Kou, Jian Yang, Pengfei Hao +4

1The Hong Kong University of Science and Technology · 2The Hong Kong University of Science and Technology (Guangzhou) · Peking University

Pragmatic Reasoning in Language ModelsLarge Reasoning ModelsInference-Time ScalingNatural Language Inference
AskPDF
Oct 10, 2026

Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI

We study neuro-symbolic natural language inference (NLI) with independently translated propositional representations of the premise and hypothesis. Before symbolic reasoning, the system must infer semantic links between their proposition-level units (atoms). Existing systems based on Abstract Meaning Representation (AMR) and Boolean satisfiability (SAT) identify these links using fixed embedding-based source selection and pretrained sentence-level NLI models not trained for atom-level linking. We introduce a trainable atom linker that jointly predicts link existence, source selection, and relation type. Without atom-pair training annotations, we treat cross-formula link structures as latent and train the linker from sentence-level NLI labels, keeping the translator and SAT reasoner fixed. We evaluate on the full public test splits of Stanford Natural Language Inference (SNLI) and Sentences Involving Compositional Knowledge (SICK), and the matched and mismatched validation splits of Multi-Genre Natural Language Inference (MNLI). Our system improves accuracy by 11.40-27.09 percentage points over a baseline applying sentence-trained NLI models unchanged to atom pairs within the same SAT pipeline. It also improves over the prior fixed-linker AMR-to-SAT system by 8.14-26.32 percentage points on SNLI and both MNLI splits, with a smaller gain on SICK.

Xuyao Feng, Antonis Bikakis

University College London, United Kingdom

Natural Language InferenceNeuro-Symbolic ReasoningWeakly Supervised Learning
AskPDF
Oct 3, 2026

Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?

In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than recording the decision. We measure how much of that evidence a small language model can recover when it is post-trained on the verdicts alone, with no human evidence labels at any stage. On ContractNLI the human evidence spans are held out until evaluation. Matching the recorded verdict and agreeing with those spans are not the same thing: across six systems the two scores are only weakly related and rank the systems differently, so accuracy is a poor guide when the citations have to be reviewable. Label-only training on the bare verdict reaches accuracy 0.896 and span F1 0.564. Rejection sampling, which keeps a generated trace only when its verdict matches the record and then picks one by an automatic source-grounding score, reaches 0.797 and 0.556, against 0.747 and 0.493 before training. Verbatim citation rises from 0.597 to 0.729 under label-only training and to 0.701 under rejection sampling. One seed on one corpus cannot say which method is better, but both improve the evidence without anyone annotating it.

Nishanth Nayakanti, Prasang Gupta, Ashutosh Bilthare +1

PricewaterhouseCoopers, U.S.

Language Model Post-TrainingRejection SamplingNatural Language Inference
AskPDF
Sep 30, 2026

UniBuc at SemEval-2024 Task 2: Tailored Prompting with Solar for Clinical NLI

This paper describes the approach of the UniBuc team in tackling the SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. We used SOLAR Instruct, without any fine-tuning, while focusing on input manipulation and tailored prompting. By customizing prompts for individual CTR sections, in both zero-shot and few-shots settings, we managed to achieve a consistency score of 0.72, ranking 14th in the leaderboard. Our thorough error analysis revealed that our model has a tendency to take shortcuts and rely on simple heuristics, especially when dealing with semantic-preserving changes.

Marius Micluta-Campeanu, Claudiu Creanga, Ana-Maria Bucur +2

Interdisciplinary School of Doctoral Studies, ♡HLT Research Center University of Bucharest, Romania · Faculty of Mathematics and Computer Science

Clinical Language Model EvaluationClinical NLPPrompt EngineeringNatural Language Inference
AskPDF
Sep 27, 2026

E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding

Natural Language Understanding (NLU) plays a crucial role in various applications, yet its performance suffers from weaknesses in handling the complexities of human languages, ranging from lexical ambiguity to high-level reasoning difficulties. Analyzing errors across diverse linguistic phenomena is crucial for NLU improvement, as it will help humans get insights to comprehensively assess models' limitations and capabilities, so optimizing models' generalization. Notably, several benchmarks contain diagnostics datasets designed for investigation and fine-grained error analysis. When highlighting the gaps in the state-of-the-art, we noted that there is no naming convention for macro and micro categories or even a standard set of linguistic phenomena that should be covered. To overcome this gap, we propose an initial hierarchy for Cross-Lingual NLU error analysis. Moreover, we propose a methodology to create an NLI hierarchical framework and applied a case study on Arabic NLU. Moreover, this paper introduces E-CONAN diagnostics dataset, a freely available dataset manually-annotated with coarse-grained and fine-grained categories based on our proposed Arabic hierarchy. E-CONAN dataset helps NLU designers better understand their models by doing error analysis and in-depth investigation. We used E-CONAN to investigate the performance of 9 pretrained language models and 5 LLMs. Results indicate that LLMs outperform pretrained models in world knowledge and commonsense reasoning macro-category, and underperform pretrained models in syntactic macro-category. Moreover, the hardest phenomena for all models is Reasoning, and the easiest phenomena for all pretrained models is Syntactic, and the easiest for LLMs is Lexico-Syntactic.

Khloud AL Jallad, Nada Ghneim, Ghaida Rebdawi

Informatics Department, Higher Institute for Applied Sciences and Technology, Damascus, Syria. · Faculty of Informatics and Communication, Arab International University, Daraa, Syria.

LLM EvaluationArabic NLPNatural Language Inference
AskPDF
Sep 26, 2026

Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs

Large Language Models (LLMs) are highly capable of natural language reasoning and appear to store a great deal of lexical knowledge, but it is still unclear how much of this knowledge they actually use when reasoning, and whether they use it in the right way. On the other hand, logic-based Natural Language Inference (NLI) systems provide transparent and formally grounded reasoning, but they need to be supplied with rich lexical knowledge to prove inferences beyond purely logical ones. In this paper, we evaluate whether LLMs can identify all lexical knowledge needed to solve NLI problems and how much this knowledge contributes to proof search in a logic-based NLI system. Our research focuses exclusively on structured lexical entailments (e.g., chinchilla⊑\sqsubseteqsmall animal) as a proxy for structured explanations for NLI problems with an entailment label. First, we curate a dataset for a new task of explaining sentential entailments with a set of lexical entailments. The dataset is used to intrinsically evaluate LLMs on generating structured lexical explanations. Then, we use NLI as an extrinsic evaluation in a simple neuro-symbolic setting, assessing whether LLMs can supply sufficient lexical relations to LangPro, a natural-logic theorem prover for natural language. The results show that the proposed task remains challenging even for hosted proprietary LLMs, and that their contribution to theorem proving is moderate: generated relations are often only partially sound and may be tailored to the specific NLI problem rather than representing generally valid lexical knowledge.

Jorryt de Jong, Stefan Moraca, Ettore Cesari +1

Utrecht University, the Netherlands · Institute for Language Sciences, Utrecht University, the Netherlands

LLM ReasoningNatural Language InferenceLogical Reasoning
AskPDF
Sep 23, 2026

UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference

The Factivity Inference Evaluation 2026 (FIE2026) classifies Chinese context-hypothesis pairs into nine ordered factivity intervals. Its evaluation metric rewards both exact predictions and proximity to the correct interval, while 64.1% of the 566 training examples belong to a single class. In preliminary experiments, several mDeBERTa classification models predominantly predict the dominant class, whereas a Huber-regression baseline produces more predictions near the correct interval but fewer exact matches. We introduce Utility-Oriented Factivity Inference (UO-FIE), a parameter-efficient system that combines exact-label supervision with graded utility. UO-FIE predicts a distribution over the nine classes and combines hard-label supervision, utility-based soft targets, scheduled class weights, and an ordinal loss. We evaluate expected-utility decoding in controlled comparisons and use ordinal calibration selected on out-of-fold predictions for the submitted system. Based on Qwen3.5-9B with LoRA, UO-FIE ranks first in the fine-tuning track with a macro utility of 0.8316. A separate prompt-based ensemble ranks third in the non-fine-tuning track with a macro utility of 0.8450.

Xinchen Xiao

Xinjiang University

Ordinal RegressionClassificationNatural Language Inference
AskPDF
Sep 23, 2026

Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding

Aggregate accuracy summarizes how often a model is correct, but not which judgments remain correct when requests change. We evaluate Jev and nine language models on ContractNLI, with repeated requests that preserve the contract and target while varying visible hypotheses, requested answers, and output order. A four-model follow-up adds an equal-call repetition control and coverage of the remaining test contracts. Corrections and regressions can cancel, leaving unchanged accuracy despite changed decisions; consistent answers can also preserve errors. Majority voting over recorded responses yields small, uncertain gains, with repeated wrong answers accounting for much of the observed error. Gold-class diagnostics further reveal different error profiles behind aggregate model rankings. Resource comparisons add distinct trade-offs: Jev is cheapest and fastest for the joint baseline, while hosted language models achieve higher accuracy. Together, these findings connect decision-level evaluation to whether additional calls improve correctness and what the resulting decisions cost.

Fan Zhang, Yankai Chen, Zhuohan Xie +11

The University of Tokyo · MBZUAI · McGill University +8

LLM EvaluationEfficient Language Model InferenceLanguage Model RobustnessNatural Language Inference
AskPDF
Sep 22, 2026

Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models

Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested in understanding how LLMs leverage abstract semantic knowledge in natural language inference (NLI), which requires sophisticated linguistic capabilities to interpret implicit meanings, contextual conceptual relationships, and semantic connections between words and phrases. To this end, we propose a methodological framework for constructing new semantic knowledge at a higher level of abstraction, which we define under the notions of semantic compatibility and incompatibility for NLI. In this framework, the meaning of the lexical-semantic relations between the premise and the hypothesis is reconfigured to achieve a more flexible semantic network that induces different reasoning paths in LLMs. These new pathways show a consistent pattern of responses that allows agreement on a single response. The results demonstrate that our proposal allows to discover and compensate for LLMs' semantic knowledge gaps in NLI, achieving significant improvements in accuracy, exceeding 10% for some models, and in particular for the non-entailment class. It is essential to note that LLMs need structured knowledge and not just more data to bridge reasoning gaps. Our hybrid approach directs attention to overlooked word relationships, allowing models to synthesize missing information. We believe that the future lies not in increasing model size, but in creating a semantic scafolding that mimics the flexibility of human thinking. Hopefully, our proposal will enable the development of more robust agents and interpretable reasoning, guiding AI toward reliable language understanding.

David Torres-Moreno, Jorge Hermosillo-Valadez

Knowledge Augmentation for Language ModelsNatural Language Inference
AskPDF
Sep 21, 2026

Linguistic Features for Interpretable Textual Entailment

Despite the success of neural models in natural language processing, their black-box nature limits interpretability and conceals the linguistic phenomena underlying their predictions. We present SLITE, an explainable hybrid model for Recognizing Textual Entailment that integrates two complementary layers of semantic analysis: a structural-relational layer, based on semantic compatibility and incompatibility between compositional entities, and a distributional-informational layer, based on structured patterns of information change between embedding-based representations of the premise and the hypothesis. We propose 17 features that combine entity-level semantic relations, polarity-sensitive lexical matching, and alignment measures over semantic sub-representations of the similarity matrix, including measures based on entropy and transfer entropy. A logistic regression trained on these features achieves an accuracy of 83% on three-class SICK and 96% on SICK-CE, outperforming IsoLex by 4 percentage points and falling within 2 percentage points of RoBERTa with a fraction of its computational complexity. Ablation studies and SHAP analysis confirm that structural-relational features are the primary drivers of classification, while distributional-informational features provide essential complementary contributions, particularly for detecting neutrality and contradiction. Our results demonstrate that further exploration of hybrid approaches is a viable and scientifically productive alternative to massive neural architectures, and we hope they will strengthen the dialogue between linguistic theory and computational modeling of inference

David Torres-Moreno, Jorge Hermosillo-Valadez, Asela Reig-Alamillo

Centro de Investigación en Ciencias, Universidad Autónoma del Estado de Morelos · Centro Interdisciplinario de Investigación en Humanidades, Universidad Autónoma del Estado de Morelos

Interpretable MLNatural Language Inference
AskPDF
Sep 15, 2026

Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?

While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This paper explores whether NLI can be performed using only interpretable, graph-based representations of evidence. We introduce a fully graph-based pipeline where the classifier never directly processes the input text. Instead, sentences are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and represented as three graphs per pair: premise, hypothesis, and a retrieved ConceptNet subgraph. These graphs are then fed into a fine-tuned 0.8-billion-parameter language model. On the SNLI dataset, our pipeline achieves 89.7% accuracy, just 1.9 points below an identically trained text-based model. On ANLI, it matches the published performance of RoBERTa-large on rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) but trails by 16 points on R1, resulting in an overall gap of 9 to 14 points compared to its text counterpart. We term this gap the price of interpretability and demonstrate that it stems from representational limitations rather than data constraints. Ablation studies further reveal that graphs and text are complementary: combining both modalities achieves 92.1% accuracy on SNLI.

Younes Boufouss, Luc Pommeret, Thomas Gerald +2

STL, LISN · STL, CNRS, LISN · LISN, STL

Interpretable MLNatural Language Inference
AskPDF
Sep 10, 2026

E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference Datasets

Natural Language Inference processes pairs of sentences to extract their semantic relations. NLI has been a hot research topic, integrated as a main component in other NLP applications. Despite significant advancements in textual inference across various languages all around the world, Arabic language still suffers from limited resources in this domain. To address this gap, this paper introduces E-CONAN benchmarks that are composed of sentences pairs from various sources: (1) automatically-translated pairs, (2) human-validated machine-translated pairs, (3) hand-crafted pairs from teaching Arabic as foreign language books, and (4) headlines pairs from different news channels containing rumors. E-CONAN contains two benchmark datasets, E-CONAN-2, a 2-way dataset (RTE) and E-CONAN-3, a 3-way dataset (NLI). Additionally, we have used E-CONAN benchmarks to evaluate 9 state-of-the-art multilingual pretrained models using zero-shot classification. Models were evaluated across the ArNLI, XNLI, and E-CONAN datasets. Results show that E-CONAN is a potentially valuable resource for evaluating model generalization and even for fine-tuning pre-trained models. Its diverse composition, derived from a combination of sources, offers a broader and more robust assessment compared to XNLI and ArNLI. In addition, we have evaluated 5 LLMs on E-CONAN-3 dataset. Moreover, we incorporated MARBERT as a representative Arabic-specific baseline and conducted performance evaluation comparison to demonstrate how Arabic-specific models scale against cross-lingual and LLM-based approaches on the E-CONAN benchmarks. Furthermore, we conducted detailed qualitative and quantitative error analysis to analyze frequent error patterns. E-CONAN benchmarks will be publicly available, we hope that it will enrich research community in Arabic textual entailment and natural language inference.

Khloud AL Jallad, Nada Ghneim, Ghaida Rebdawi

Higher Institute for Applied Sciences and Technology, Damascus, Syria. · Arab International University, Daraa, Syria.

Multilingual Language Model EvaluationArabic NLPNatural Language Inference
AskPDF
Sep 4, 2026

LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics

Does a simplified legal clause still say what the original said? The checks in current use cannot establish that it does: requiring an identical pair to score highest and an unrelated pair lowest moves lexical overlap and legal force together, so any monotone function of token overlap satisfies both. Our remedy is a dissociation, an item holding surface form fixed while legal force moves. We release LexFlip, 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving 0.93 of the tokens, with a harness scoring metrics, regressors and prompted judges alike. The seven embedding and BERTScore metrics we test spend only 0.022 to 0.039 of their identical-to-unrelated range on such an edit, against 0.670 for bidirectional NLI, the one family the identical-pair check would disqualify. On FrJudge, against a measured human ceiling of r=0.597, a bare length feature outscores every semantic metric and has the lowest margin we measure.

Gaurab Baral

University of Cincinnati

Legal NLPSemantic Textual SimilarityNatural Language Inference
AskPDF
Aug 25, 2026

The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure

The imperfective paradox provides a useful test of compositional semantic analysis. Recent work constructs an NLI benchmark and reports that models frequently infer completed telic events from progressive descriptions, attributing this behavior to a Teleological Bias. It further argues that prompting interventions cause a Calibration Crisis. We reexamine the benchmark and conclusions and show that it is substantially affected by conceptual and evaluation mis-specifications. We identify three conceptual mis-specifications. In particular, Aspectual Reduction affects the benchmark construction, analysis, experiments, and conclusions. Under a strict NLI standard, 76% of Group A instances do not explicitly rule out culmination. In our native-speaker annotation, 38% of Group A examples and 29% of the Group C examples were judged to permit an alternative interpretation. To control these issues and lexical variation, we construct Lexically Matched Minimal Pairs. At the evaluation level, we formulate event-semantic NLI as a Multi-step Reasoning Problem and assess both intermediate semantic decisions and final predictions. Our results show that models often do not affirm culmination but nevertheless accept the corresponding simple-past hypothesis, a pattern we characterize as Sufficiency Bias. We further show that prompting interventions produce a Decision Shift among labels without reliably improving the underlying semantic understanding and reasoning. Intermediate and oracle-guided analyses identify two additional failure modes: errors in compositional aspectual classification and Surface-form Attraction toward surface-associated answers. Our experiments on Qwen-7B with suitable prompts, GPT-5.4, and Qwen-72B provide initial evidence for the context sensitivity of aspectual classification and suggest that these models can achieve performance comparable to that of human annotators.

Kaiqiao Han, Yizhou Sun

University of California, Los Angeles

Temporal Reasoning in Language ModelsLLM EvaluationNatural Language InferenceLanguage Modeling
AskPDF
Aug 19, 2026

Structure, Association, and Decision Value: Representation-Based Difficulty Estimation for Adaptive Inference in African-Language NLI

We ask whether internal representation statistics can provide useful example-level difficulty signals for adaptive inference in multilingual African NLP, and find that they cannot in this setting. Studying natural language inference across 15 African languages with frozen off-the-shelf checkpoints, we report four results. First, AfriXNLI's English configuration shares 1,047 of its 1,050 examples verbatim with XNLI evaluation data, and one widely used NLI checkpoint scores 1.000 on that test split, consistent with XNLI test exposure. Because AfriXNLI is derived from XNLI, its English, French and Swahili configurations cannot serve as clean evaluations for XNLI-trained models. Second, parameter count does not reliably order capability across African languages: our larger checkpoint is better in seven languages and worse in eight, with no significant aggregate difference. Third, across three multilingual representation spaces, angular dispersion is consistently more language-determined than effective rank, so pooled correlations can inflate one and mask the other. Fourth, the association that survives language control depends on the target: effective rank predicts probability gain from escalation but not whether escalation changes the prediction, while cheap-model confidence shows the opposite pattern; the two targets correlate at only 0.655. Under the tested models, signals, and compute budgets, no evaluated signal makes adaptive routing preferable to always-expensive inference, although an oracle exceeds it by 11 accuracy points at 60% of the compute. Our central methodological finding is that a representation statistic can be statistically significant for one notion of computational benefit while being irrelevant to another, and therefore be a poor decision variable.

Toheeb Ogunade

University of Lagos

Adaptive InferenceAfrican Language ProcessingMultilingual Language Model EvaluationLow-Resource Language ProcessingNatural Language InferenceRepresentation Geometry in Language Models
AskPDF
Aug 19, 2026

Identifying Implicit Premises for Logical Reconstruction of Argument Graphs

The logical reconstruction of argument graphs from natural language text is challenging because of the prevalence of enthymemes (i.e., arguments with implicit premises). There are natural language processing methods for identifying enthymemes in text, and there are symbolic methods based on abduction for identifying missing premises in a logical representation of enthymemes. However, there is a need for methods to generate implicit premises to logically show a known entailment or contradiction relationship between a pair of statements. To address this, we propose a neuro-symbolic pipeline that uses large language models (LLMs) to generate intermediate implicit premises that are translated into logical formulae and used with logical formulae representing explicit premises and explicit claims to show the logical relationships between them (entailment, contradiction, or neutrality). Our approach is evaluated on the Microtext Argumentative Corpus.

Xuyao Feng, Anthony Hunter

Department of Computer Science, University College London, United Kingdom

Computational ArgumentationNeuro-Symbolic ReasoningNatural Language Inference
AskPDF
Jul 21, 2026

Selection Shapes the Boundary: A Replication of Monotonicity and Label Agreement in Unselected NLI Populations

Prior work on human label variation (HLV) in natural language inference (NLI) has often relied on re-annotation resources that select items by disagreement level. An earlier study (Choi, 2026, arXiv:2607.15870) found that hypotheses containing non-upward monotonicity operators showed somewhat higher label entropy in ChaosNLI (Cliff's delta = -0.284), a difference that study reports as sensitive to tagger error. In its SNLI and MultiNLI portions, ChaosNLI re-annotates only items whose majority label carries exactly three of five votes. We replicate this boundary in the unselected populations that ChaosNLI was drawn from. We use the SNLI and MultiNLI development sets with the same operator tagger and a four-level ordinal agreement outcome, under a plan frozen in our working repository before analysis. The planned prediction fails. All seven contrasts return a positive Cliff's delta (non-upward items agree slightly more, not less), the only significant confirmatory contrast has the opposite sign to the planned direction, and every effect is far below our smallest effect size of interest (0.10). Robustness checks support the measurement: simulated tagger misclassification shrinks the effects rather than manufacturing them, and a manual re-tagging audit reaches four-class agreement of 0.875 on a fresh 200-item sample. We conclude that the earlier negative boundary is plausibly a structure conditional on low-agreement selection rather than a population-level property, and that HLV structure claims built on selected re-annotation resources should state their selection conditional explicitly.

Haram Choi

University of Bremen

Annotator DisagreementSelection BiasNatural Language Inference
AskPDF
Jul 17, 2026

How Much Human Label Variation Does Formal Semantic Structure Explain? Group-Level Effects and Item-Level Ceilings in NLI

Human label variation in natural language inference (NLI) is increasingly treated as a signal to be measured rather than as noise to be removed. We ask whether one candidate source of that signal, formal semantic structure such as negation, quantification, and monotonicity, changes how much annotators disagree and what they disagree about. We tag the SNLI and MNLI items of ChaosNLI, each labeled by 100 annotators, with a rule-based monotonicity tagger, check the tagger by hand on a sample of the same items, and answer three questions. At the group level, hypotheses that are not purely upward monotone attract somewhat more disagreement, but an error sensitivity analysis shows that this difference is sensitive to tagger error. At the item level, formal structure explains only a few percent of the variation and cannot pick out the items that attract high disagreement. In composition, the kinds of disagreement recorded by VariErr and LiTEx do not differ detectably across the formal boundary. Formal structure therefore belongs in the inventory of disagreement sources, with a small and bounded weight. ChaosNLI was built from low-agreement items, and every claim holds within that scope. Analysis decisions were written in a version-controlled research log before the corresponding results were computed, and negative results are reported in full.

Haram Choi

University of Bremen

Annotator DisagreementNatural Language Inference
AskPDF
Jun 3, 2026

SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs

Many human-centered tasks, including natural language inference (NLI) and emotion recognition (ER), have multiple plausible interpretations, leading to label ambiguity and challenging disagreements across human annotators. As LLMs are increasingly deployed in real-world settings, faithfully modeling such ambiguity is essential to identify contested inputs, preserve variability in ambiguous cases, and capture the full distribution of human judgments. Yet, existing LLM alignment approaches have predominantly assumed a single correct label, excluding annotator disagreement during optimization. Instead of treating this ambiguity as noise, we show how to treat it as information that improves model behavior through a new algorithm called SMARTLY HANDLING AMBIGUOUS LABELS IN ALIGNING LLMS (SHALA-LLM). This reinforcement learning framework provides a new way for LLMs to learn directly from annotator distributions while dynamically prioritizing highly ambiguous samples during optimization. Experiments on ambiguity-sensitive NLI and ER benchmarks, including ChaosNLI, GoEmotions, and MSP-Podcast, demonstrate that SHALA-LLM improves agreement with annotator label distributions, e.g. on ChaosNLI, it reduces Jensen-Shannon Distance by up to 62.1%. At the same time, SHALA-LLM improves F1 by up to 16.7%, showing that modeling annotator disagreement can also strengthen classification performance.

Jingyao Wu, Ashley Wang, Keane Ong +2

MIT Media Lab, Massachusetts Institute of Technology · National University of Singapore

RL for Language ModelsLLM AlignmentLabel Distribution LearningNatural Language Inference
AskPDF
Jun 2, 2026

From Script to Semantics: Prompting Strategies for African NLI

Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains underexplored especially under pure prompting without fine-tuning. We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa using the AfriXNLI benchmark. We evaluate five prompting strategies Baseline (zero-shot), Script-Aware, Language Specific, Contrastive, and Native-Label Self-Translation (NL-STP) across two mid-sized open weight models (Llama3.2-3B and Gemma3-4B). To isolate the effect of prompt design, the effect of few-shot examples and Chain-of-Thought reasoning is eliminated in our study. We find a significant difference in performance of class wise across strategies with highly neutral class collapse and high prediction skew in some configurations. Contrastive prompting proves to be the most reliable and steadily improving strategy over language and model and has better balance of class behavior and balance of overall accuracy gains. Notably, well-constructed prompts are sufficient to beat more powerful baselines that are provided with few-shot prompts and Chain-of-Thought prompts. We have found that prompt formulation is essential to multilingual NLI with low-resource languages and that language aware decision structuring can be used to meaningfully enhance robustness in resource challenged settings.

Anuj Tiwari, Terry Oko-odion, Hannah Nwokocha

Noida Institute of Engineering and Technology1, India1 · ML Collective1,2,3, Nigeria2,3

Multilingual Language Model EvaluationLLM PromptingLow-Resource Language ProcessingNatural Language InferenceAfrican Language Processing
AskPDF
Jun 2, 2026

SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding

Frontier LLMs perform well in Western contexts, but remain poorly tested on underrepresented cultures such as those in Southeast Asia (SEA). Existing NLI benchmarks are largely Western-centric, translation-derived, or monolingual, limiting their ability to measure culturally grounded reasoning. We introduce SEA-NLI, a native, culturally grounded NLI benchmark covering eight SEA countries in English and native regional languages, verified by native speakers. Across 17 encoder and decoder models, we observe a low performance from all models, especially for knowledge-intensive categories such as Languages and Science and Technology. Our analysis shows that failure cases mainly stem from missing SEA cultural knowledge: SEA-adapted models and culture-aware prompting improve performance, while CoT prompting offers limited gains.

Peerawat Chomphooyod, Jian Gang Ngui, Yosephine Susanto +5

1Chulalongkorn University · 2AI Singapore · 3MBZUAI +1

Multilingual Language Model EvaluationCross-Cultural Language Model EvaluationCultural AlignmentCultural Knowledge in Language ModelsNatural Language Inference
AskPDF
Jun 2, 2026

Sample-Size Scaling of the African Languages NLI Evaluation

African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief of monotonic increase with increased data, we find a strongly language sensitive and often non-monotonic scaling behavior. Some languages show early saturation or decrease in performance with sample size as well as high variance in low resource regimes. These results indicate that the volume of data is not enough to guarantee stable profits to African NLI, creating the necessity of language sensitive datasets creation and stronger multi-lingual modelling strategies.

Anuj Tiwari, Oluwapelumi Ogunremu, Terry Oko-odion +2

Noida Institute of Engineering and Technology1 · ML Collective1,2,3,4,5

Multilingual Language Model EvaluationLow-Resource Language ProcessingNatural Language Inference
AskPDF
Jun 1, 2026

Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling

Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential---yet these datasets have never been rigorously audited. Our first contribution is to present a systematic human inspection of the validation split of FOLIO and a subset of MALLS test instances, finding that approximately 42.5% and 42% of entries, respectively, contain incorrect FOL formalizations (i.e., ground truth labels), with additional rates of ambiguous NL sentences (17.8% and 51%) and incorrect NLI labels in FOLIO (8.4%). Our second contribution is to develop and release corrected ground truths for such datasets, showing that annotation errors distort model evaluation on a reference benchmark task: testing three state-of-the-art LLMs (Gemma~4 31B-it, Qwen3-30B-A3B, and GPT-4o-mini) with the corrected ground truths yields accuracy gains from +11 to +23 percentage points. Motivated by these findings, we propose an LLM-based framework to support humans in manual reviewing NL-to-FOL datasets. By directing reviewers toward the most error-prone instances, we empirically show that it is possible to achieve 90% dataset accuracy after reviewing fewer than 20% of instances, compared to over 76% required by unguided review. We release all human-verified annotations and the code for our framework.

Andrea Brunello, Cristian Curaba, Luca Geatti +3

University of Udine, Italy

LLM-Assisted AnnotationHuman-in-the-Loop AnnotationNatural Language Inference
AskPDF
May 28, 2026

Metric-Dependent Annotation Saturation for Learning from Label Distributions

When annotators disagree on a label, the disagreement itself carries signal - and the number of annotators needed to capture it depends on the evaluation metric. We fine-tune NLI models on label distributions subsampled from ChaosNLI, a dataset providing 100 independent annotator judgments per item, and identify metric-dependent saturation. In our 3-class NLI setting, entropy correlation - whether the model identifies which items elicit disagreement - requires N ~ 20-50 annotators to converge, while distributional match (KL divergence) saturates by N ~ 10 (87-95% of improvement across five model seeds); the specific thresholds are estimates for this setting, and it is the phenomenon, not the constants, that we expect to generalize. This finding rests on a prior observation: soft labels carry item-specific signal that label smoothing cannot replicate. Across five smoothing intensities, entropy correlation clusters at r ~ 0.45-0.49, while soft labels reach r = 0.643 (p < 0.001); per-item analysis traces this gap to smoothing's inability to distinguish ambiguous items from clear ones. The soft label advantage replicates across two architectures (DeBERTa, RoBERTa) and a non-NLI-pretrained baseline; differential saturation additionally appears in an exploratory cross-domain evaluation on content safety. These results suggest that annotation budgets should be informed by the target evaluation metric rather than set uniformly.

Guneet Kohli

Apple

Soft-Label LearningAnnotator DisagreementLabel Distribution LearningNatural Language Inference
AskPDF
May 25, 2026

Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those labels is unclear. We investigate this in Natural Language Inference using controlled premise-hypothesis pairs that differ by a single semantic transformation. Using layer-wise activations, we estimate operation-level subspaces via SVD and test their causal relevance through activation steering in four open-weight decoder models. Transformation effects are decodable with 84.884.8-99%99\% accuracy and occupy partially distinct but overlapping subspaces, exceeding random-subspace baselines. Steering experiments show that these directions causally influence predictions, though steerability varies across models; cross-operation steering further reveals structured interference and a dissociation between subspace selectivity and cross-operation independence. These findings indicate that the models encode not only that a hypothesis relates to a premise but also, in part, how it does so, implying that mechanistic analysis and control should operate at the level of semantic operations rather than predicted labels alone.

Nura Aljaafari, Marco Valentino, André Freitas

University of Manchester, United Kingdom · University of Sheffield, United Kingdom · Idiap Research Institute, Switzerland +1

Mechanistic InterpretabilityLanguage ModelingNatural Language Inference
AskPDF
May 20, 2026

Tracing the ongoing emergence of human-like reasoning in Large Language Models

Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker will pay only if the lawn is mowed, whereas If you are hungry, there is pizza in the oven implies that pizza is available regardless of the hearers hunger. Large Language Models - LLMs - show human-like performance on many tasks, yet it remains unclear whether they reason like humans. To address this, we conducted a population-matching experiment assessing how twentyfive LLMs compute conditional inferences across four languages, compared to an equal number of humans per language. We find that humans enrich logical reasoning through pragmatic inferences across languages. Model behavior is more variable. Some LLMs perfectly follow the truth-table of conditionals but they ignore pragmatic inferences, while others deviate from the truth-table, adhering to a single interpretation across the board, thus reflecting accurate rule-based processing but not human-like reasoning. Overall, LLMs are accurate semantic operators, but fail to capture the pragmatic enrichments characteristic of human reasoning. Crucially, LLM accuracy is neither predicted nor boosted by open vs. closed status, training orientation, or architecture type, suggesting that pragmatic reasoning is still an emerging ability in the cognitive toolkit of artificial systems.

Paolo Morosi, Nikoleta Pantelidou, Fritz Günther +2

Departament de Filologia Catalana, Universitat Autònoma de Barcelona, Barcelona 08193, Spain. · Institut für Psychologie, Humboldt-Universitat zu Berlin, Berlin 10099, Germany. · Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona 08010, Spain

Logical ReasoningPragmatic Reasoning in Language ModelsLLM ReasoningNatural Language Inference
AskPDF
Apr 30, 2026

ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts

In this article, we introduce ViLegalNLI, the first large-scale Vietnamese Natural Language Inference (NLI) dataset specifically constructed for the legal domain. The dataset consists of 42,012 premise-hypothesis pairs derived from official statutory documents and annotated with binary inference labels (Entailment and Non-entailment). It covers multiple legal domains and reflects realistic legal reasoning scenarios characterized by structured logic, conditional clauses, and domain-specific terminology. To construct ViLegalNLI, we propose a semi-automatic data generation framework that integrates large language models for controlled hypothesis generation and systematic quality validation procedures. The framework incorporates artifact mitigation strategies and cross-model validation to improve annotation reliability and ensure legal consistency. The resulting dataset captures diverse reasoning patterns, including paraphrasing, logical implication, and legally invalid inferences, thereby providing a comprehensive benchmark for Vietnamese legal inference tasks. We conduct extensive experiments on the ViLegalNLI using multilingual models, Vietnamese-specific pretrained language models, and instruction-tuned large language models. The results show that few-shot LLM configurations consistently achieve superior performance, while performance is significantly influenced by hypothesis length, lexical overlap, and reasoning complexity. Cross-domain evaluations further reveal the challenges of generalizing legal inference across distinct legal fields. Overall, ViLegalNLI establishes a foundational benchmark for Vietnamese legal NLI and supports future research in legal reasoning, statutory text understanding, and the development of reliable AI systems for legal analysis and decision support. The dataset is publicly available for research purposes.

Nhung Thi-Hong Duong, Mai Ngoc Ho, Tin Van Huynh +1

University of Information Technology, Ho Chi Minh City, Vietnam. · Vietnam National University, Ho Chi Minh City, Vietnam.

Legal ReasoningNatural Language Inference
AskPDF