Legal Natural Language Processing Benchmarks

When two texts describe the same expression, standard metrics based on lexical overlap or whole-text similarity may fail to detect meaningful differences in how that expression is framed. We propose a framework to evaluate semiotic alignment between texts, where a semiotic profile encompasses both the contextual meaning and the discourse references made salient by a text. Our approach yields two scores, Semiotic Fidelity and Semiotic Coverage, estimating how much of one text's profile is supported by the other and how much of the other's profile it recovers. Experiments show that coverage is typically lower than fidelity, and that alignment between LLMs and human-curated data is highest at low sampling temperatures, while higher temperatures reduce this alignment.

Financial language models can transform unstructured firm-specific news into structured decision signals, but financial AI research lacks an integrated deployment framework for evaluating whether those signals remain useful in financial decision systems. Computer science research has developed strong methods for time-series forecasting, text classification, multimodal stock prediction, graph-based market modeling, and machine-learning operations, yet these streams do not provide a domain-specific protocol that jointly tests financial language-model outputs under event-time observability, probability calibration, execution timing, transaction costs, liquidity constraints, capacity limits, operational diagnostics, and statistical inference. We introduce MFAST, a Market-Friction-Aware Sentiment-to-Trading framework that converts timestamped financial text into auditable, reproducible, and market-feasible trading decisions. The application is news-based trading, where firm-specific text must be linked to securities before portfolio decisions can be evaluated. The framework links Refinitiv News Analytics to Center for Research in Security Prices (CRSP) equity data, restricts the primary out-of-sample evaluation to post-release news outside disclosed foundation-model data-freshness periods, and adds a public replication arm using open financial text and public price data. Results show that decoder-only language models outperform encoder baselines and dictionary sentiment in classification, calibration, return prediction, and net portfolio performance, while operational diagnostics reveal trade-offs among accuracy, latency, memory, throughput, and inference cost. The paper shows that credible evaluation of financial language models requires an end-to-end engineering approach combining language understanding, temporal discipline, market-friction-aware deployment, and reproducible validation.

Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the best of our knowledge, the first benchmark for predicting non-pecuniary damage (NPD) awards at the European Court of Human Rights (ECtHR) from case information when no statutory formula or explicit calculation rule determines the amount. ECtHR-NPD contains 14,575 cases with case-level awards in nominal euros, chronological splits, and a protocol separating target construction from model input. We evaluate a battery of methods, including constant predictors, gradient-boosted trees, retrieval methods, fine-tuned encoder language models (LMs), prompted decoder LMs, and knowledge-augmented agents. Our results show that more sophisticated LM and agentic approaches do not consistently outperform the strongest feature-based baseline. All model families struggle to identify zero awards and to calibrate high-award predictions, with further degradation on the Challenging test view, making ECtHR-NPD a challenging testbed for current state-of-the-art open-weight and proprietary LMs.

We submit MéTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native Quebec-French benchmark of grammatical minimal pairs) and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE (General Language Understanding Evaluation) protocol that combines French task-data translation with rank-16 LoRA (Low-Rank Adaptation) produces a sharp task-type gradient: relational tasks gain measurably, while world-knowledge tasks regress. Bilingual Lexicon Induction aligns the French embeddings to GPT-2 at p@1 = 68.84 +/- 8.61%, 18X above chance, suggesting cross-lingual alignment tracks acquired grammatical competence rather than training duration. An ablation study shows that single-token zero-shot scoring is dominated by tokenizer and template artifacts at the child scale, motivating tokenizer-swap sensitivity, placebo-controlled prompting, and native-language minimal-pair benchmarks as standard diagnostics.

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.

We present the IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a multilingual financial question answering task over English SEC filings and multilingual news articles (English, Chinese, Japanese, Spanish, Greek) for four companies. Our central observation is that the 344 development questions divide into two families requiring fundamentally different approaches: structured numeric types (R&D ratio, cash flow, capital expenditure) are best answered by direct keyword extraction on filing text, while synthesis types (investment strategy, capital allocation, top-three revenue focuses) require rule-based multilingual news passage selection. A dataset analysis reveals that 17-18 of 19 ground-truth reference answers per synthesis type share an exact evidence label prefix, whose unigram tokens contribute directly to ROUGE-1 overlap. The final system achieves development ROUGE-1 approximately 0.395, a 60% relative improvement over a generic RAG baseline (approximately 0.247), and ranks 3rd of 12 teams on the official test set with ROUGE-1 = 0.3071, Precision = 0.2821, and Recall = 0.4044.

As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before taking actions. We introduce KC-Bench, a controlled multi-turn benchmark for measuring this capability across world-knowledge conflicts, input inconsistencies, and multi-source temporal conflicts. Its 238 tasks are manually screened from more than 1,000 generated candidates and combine a user simulator, stateful tools, deterministic environment assertions, an open-source natural-language evaluator, and human trajectory verification. Evaluation of nine models, including DeepSeek-V4-Flash, GLM-5.2, and MiniMax-M3, shows substantial cross-domain variation: no model handles factual correction, identity consistency checking, and temporal conflict resolution reliably across all settings. In the simulated environments, missed conflicts can propagate to tool calls or synthetic protected-data flows. KC-Bench isolates this model-level behavior rather than ranking complete agent frameworks, and provides a reproducible diagnostic for developing conflict-aware reasoning and execution safeguards.

In frame semantics, sentence comprehension is assumed to proceed by relating lexical meaning to background knowledge called semantic frames, thereby enabling readers to implicitly enrich the text with unstated information. Recent large language models (LLMs) have achieved strong performance across a wide range of downstream tasks. However, it remains unclear whether they can reproduce the kinds of implicit enrichment that humans naturally make during comprehension. To address this question, we introduce FrameBench, a benchmark grounded in frame semantics. FrameBench consists of multiple-choice questions that test whether models distinguish the frames evoked by the same verb across contexts. We construct the benchmark for English and Japanese using FrameNet-style resources and a generation-and-verification pipeline with native-speaker judgments. Our experiments on a diverse set of models reveal challenges for small models, while several large models surpass the human reference scores. We release the constructed FrameBench dataset and the code for dataset construction and evaluation at https://github.com/SasanoLab/FrameBench.

General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs. AVA comprises 171,007 contrastive triplets derived from 163 heterogeneous ontologies using hierarchy inversion, relation substitution, and disjointness injection. Each triplet contains an ontology statement, a semantically equivalent paraphrase, and a logic-sensitive hard negative with contradictory relational meaning. We evaluate more than 25 state-of-the-art embedding models and find substantial limitations: the best model achieves only 0.739 triplet accuracy, while hard negative accuracy falls to 0.135. Fine-tuning improves discrimination by a large margin but transfers poorly to downstream Semantic Web tasks, including taxonomy discovery and ontology alignment. Further analysis suggests that improvements stem partly from perturbation-specific pattern recognition rather than robust ontological understanding. These findings reveal a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark performance translates to Semantic Web competence.

Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see what changes. But a latent fires at many tokens, and the effect has to be measured at one of them. The convention is to measure where the latent fires hardest. That choice is almost never reported, and it is not made by the experimenter: it is made by the dictionary under evaluation. Change the dictionary and the measurement moves to a different token. We show this is not a detail. Take two sparse autoencoders released by Google for the same model and match their latents by decoder similarity: even among the pairs the two dictionaries encode almost identically, they pick different tokens for a large share of them. Two dictionaries compared under the usual protocol are therefore very often compared at different places. To separate the convention from the dictionaries we train six autoencoders from one initialisation, differing only in fitting choices, so that a latent means the same thing in each. Most of the variance such a comparison reads as "these dictionaries disagree about this latent" turns out to be the position instead: it falls from 7.6% and 11.9% of variance to near zero once every dictionary is measured at the same token. More evaluation data does not rescue it. Across a sixteenfold range of corpus sizes the dictionaries agree less about where to measure, not more, so the problem grows with scale. The correction is one line of evaluation code. We give the protocol an ablation-based causal number must report to be comparable across papers, and an audit of five published papers against it. In short: a causal number reported without its position describes the token it was taken at as much as the latent it was taken from.

The Seungjeongwon Ilgi, a UNESCO Memory of the World record, is only 37.4% translated, and the most conspicuous failure mode in automatic translation is the person name -- a misread name corrupts the historical fact rather than merely the surface. Low-resource historical domains have no expert gold standard for entity translation, so practitioners substitute a knowledge base (KB) for the gold. That KB is the same resource injected into the system: scoring becomes self-referential and the metric measures instruction compliance rather than translation quality. We measure this loop. Using expert person-name annotations from the National Institute of Korean History as a gold independent of the injection pipeline, we hold the entity set fixed and vary only the provenance of the correct reading. Of 527 expert-annotated mentions, only 31.1% lie outside the injection pipeline, and the residual loop is not uniform -- in the overlapping segment the injected reading agrees with the human translation 97.8% of the time against 70.1% in the independent one, so the segment that looks healthiest is the one the loop is holding up. Across four models, a difference-in-differences analysis shows the gain from KB injection is confined to the segment whose gold shares the injected resource; in the independent segment it is at or below zero. Post-injection preservation clusters in a narrow 0.910-0.996 band even though baseline capability differs fivefold, so the reported gain is the complement of prior performance and weaker models appear to improve more dramatically. On an independent sample built by removing the construction filter, the measure replicates within model (overlapping intervals) while discriminating between models (non-overlapping intervals) -- it reflects a property of the model, not of the sample.

Understanding concepts is fundamental to generalization. Despite their impressive performance on a wide range of tasks, Large Language Models (LLMs) still struggle with genuine concept understanding. Prior work has evaluated conceptual understanding in LLMs using natural-language benchmarks or narrowly scoped synthetic tasks, but these settings often conflate multiple skills or lack precise control over the underlying concepts and their properties. To support controlled probing of concepts in LLMs, we design tests on their core properties: abstraction, compositionality, and groundness. We set up a concept-centric benchmark, targeting spatial concepts such as direction, distance, topology, and their compositions, and use question answering tasks serving as a proxy. We conduct extensive experiments across multiple LLM architectures and training regimes to analyze how model scale and design impact conceptual understanding. The results reveal clear limitations in current LLMs and provide insights into the factors shaping their ability to acquire and compose structured concepts. Our findings shed light on how concept-based LLMs can be redesigned for improved information access and knowledge management. The code will be available at https://github.com/rd20karim/concept-probing.

Financial sentiment classifiers are commonly evaluated against human labels, but strong linguistic performance does not necessarily imply economically useful return predictability. This study separates these questions through two experiments. First, we construct a unified three-class benchmark from five financial text datasets and compare TF--IDF Naive Bayes, off-the-shelf FinBERT and Financial-RoBERTa encoders, zero-shot Qwen2.5-7B, and QLoRA-adapted Qwen2.5-7B, LLaMA3-8B, and Mistral-7B models. Mistral-7B achieves the best test accuracy (0.8840) and macro-F1 (0.8771), while QLoRA raises Qwen2.5's macro-F1 from 0.7274 to 0.8615. An inverse-frequency class-weighted loss does not improve Qwen2.5. Second, we evaluate economic validity on a temporally separate 2019 Benzinga sample containing 10,637 unique headlines and 13,115 headline--stock observations for a fixed S&P~100 universe. Model probabilities are converted into continuous sentiment scores, aggregated by stock and signal date, and aligned with next-session returns over one-, two-, three-, and five-day horizons. All seven downstream models produce positive but small mean rank information coefficients at the one-day horizon; the largest is 0.0143 for FinBERT. None of the 28 model--horizon tests remains significant after Newey--West inference and false-discovery-rate correction. Portfolio results likewise fail to establish a robust advantage for the best-performing classifiers. The findings show that QLoRA is effective for financial sentiment adaptation, while also documenting a clear gap between classification accuracy and tradable cross-sectional signals.

Shadow trading -- trading in a peer firm's securities on the basis of material nonpublic information (MNPI) about an "economically linked" company -- is a novel and contested theory of insider trading liability, first prosecuted in SEC v. Panuwat (2023). Enforcing it requires identifying economically linked firms ex ante, a determination the SEC makes only after the fact using mass market surveillance infrastructure. We ask whether NLP can do what the SEC's theory presumes insiders already know: identify peer firms ex ante from publicly mandated disclosures. Using a two-stage LLM pipeline applied to Item 7 (Management's Discussion and Analysis) sections of SEC 10-K filings, we score semantic similarity across 30 M&A events spanning five industries and relate similarity to announcement-day abnormal stock returns. On the Panuwat fact pattern itself the pipeline recovers Incyte among the closest peers, a sanity check on the one case with a known outcome. Across the full dataset, however, we find no association: pooling 217 peer observations, the within-event rank correlation between similarity and abnormal return is +0.07 (permutation p = 0.37), and the mean per-event Spearman correlation is +0.05 with a 95% confidence interval of [-0.08, +0.18] -- narrow enough to exclude any moderate relationship rather than merely failing to detect one. A case-level reading agrees: 14 of 30 events support the hypothesis, 12 contradict it, and 4 are ambiguous. We also find that Incyte fell outside the standard $2B-$10B mid-cap band on the day before the announcement, complicating the "mid-cap oncology" category the SEC invoked. These results are exploratory and bound to this pipeline, corpus, and return measure, but they put pressure on the empirical premise of shadow trading enforcement and bear on constitutional questions surrounding the SEC's financial surveillance infrastructure.

This paper introduces SCHEDBench, a natural-language benchmark for evaluating combinatorial scheduling constraint faithfulness under surface-form variation. Grounded in canonical scheduling instances and solver-derived feasibility and optimality, SCHEDBench assesses whether large language models (LLMs) generate schedules with the same constraint-feasible behavior across varied natural-language (NL) surface forms. SCHEDBench spans 1,132 instances across job-shop scheduling problems (JSP), single and multi-mode resource-constrained project scheduling problems (RCPSP), nurse rostering/scheduling, and curriculum timetabling problems of varying difficulty. Instances are templated into natural language problems using domain-specific templates, themed entities, lexical-syntactic template rephrasing, and constraint-level surface-form variation, with reference solutions verified for feasibility and objective optimality. Across thirteen frontier and open-weight LLMs, we find that models are not reliably invariant to semantically equivalent renderings of the same scheduling problem. Surface-form variation reduces feasibility and induces above-noise shifts in per-instance hard-constraint violations on matched instances. Among the tested isolated axes, constraint reordering yields the clearest above-noise sensitivity.

We introduce Earnings25, a finance-domain benchmark for evaluating automatic speech recognition (ASR) on English-language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-language S&P 500 earnings calls from Q4 2025, and (ii) testset-segmented, a 46-hour industry-balanced set of 290 segments sampled from English-language U.S. earnings calls in 2025. The benchmark provides aligned transcripts and structured metadata, including speaker roles, industry labels, and call structure, enabling speaker- and industry-aware evaluation beyond aggregate word error rate (WER). We report reproducible baselines for Whisper and Parakeet-TDT using standardized scoring.

Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or search system, yet the model that tops a leaderboard is rarely the best choice for a given deployment. This report develops a practical, evidence-based framework for embedding model selection, built on a benchmarking study that evaluates T3EM (Text 3 Embedding Model), a commercial API-based embedding model, against a broad set of open-source alternatives on English-language retrieval tasks, and situates these findings within the wider Massive Text Embedding Benchmark (MTEB) landscape spanning classification, clustering, semantic similarity, reranking, pair classification, bitext mining, and summarization. Beyond raw benchmark scores, the report traces the full path from embedding model to retrieved result -- how embeddings are produced, how they are indexed and searched at scale, and how document chunking strategy shapes retrieval quality -- so that model choice can be reasoned about as one decision within a complete retrieval pipeline rather than in isolation. The result is a consolidated set of practical recommendations for selecting an embedding model according to task, latency, cost, and deployment constraints.

We present DS@GT's submission to FinMMEval 2026 Task 1, a multilingual financial exam question answering benchmark spanning English, Spanish, Greek, Chinese, and Hindi. Financial certification exams such as the CFA, EFPA, and CPA demand structured domain reasoning that standard NLP benchmarks do not capture, and this challenge compounds across languages where retrieval and representation infrastructure is underdeveloped. We build a retrieval-augmented pipeline on LangGraph that detects query language and retrieves semantically relevant exemplars from a 30,209-entry multilingual knowledge base using BGE-M3 embeddings and FAISS indexing. The system then scores answers via Retrieval-Augmented Direct Scoring (RADS), reading next-token log-probabilities over candidate option letters rather than generating free-form output. For low-resource languages, we fuse per-language and cross-lingual retrieval indices using weighted Reciprocal Rank Fusion. Model selection is language-routed: Qwen3-14B for Arabic, Chinese, and Hindi; Qwen2.5-14B for English; and Llama-3.1-8B for Greek, a routing derived from empirical ablations that reveal substantial language-asymmetric performance gaps. Notably, chain-of-thought prompting significantly degrades Greek accuracy (90.7% to 20.9%), and enabling Qwen3's default thinking mode collapses Arabic RADS performance to near-chance levels. Our results indicate that effective multilingual financial reasoning requires language-aware retrieval, model routing, and deliberate scoring strategy selection.

We present CUP, a Greek book retrieval benchmark consisting of 868 catalog records and 104 expert-annotated queries with graded relevance judgments. We evaluate sparse (BM25), dense (sentence-transformers), hybrid, and LLM-assisted retrieval methods in this book-search setting. Multilingual embeddings outperform Greek-specific models, while hybrid retrieval performs best overall. A query-level analysis shows that BM25 excels at named-entity queries, while dense and hybrid methods improve natural-language, noisy, cross-lingual, and concept queries. Field-aware prompting has model-specific effects, while LLM TOC summarization improves TOC-only retrieval and LLM post-filtering improves early-stage retrieval at a high cost. Overall, CUP enables real-world evaluation of Greek retrieval across lexical, semantic, noisy, and cross-lingual queries.

Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual representation. To this end, we introduce the Real World Voice EQ Bench, a multidimensional benchmark for evaluating voice AI across text-to-speech (TTS), speech-to-speech (STS), speech understanding (SU), and automatic speech recognition (ASR). Our evaluations indicate that performance is highly dimension-specific. For TTS, naturalness, expressiveness, identity stability, and reliability are largely independent evaluation dimensions. For STS, access to audio does not guarantee use of vocal affect, and some agents remain largely transcript-driven. For SU, models perform unevenly across paralinguistic tasks. For ASR, real world accent, emotion, noise, and conversational conditions expose failures that are not captured by established clean-speech benchmarks. Together, these results show that voice AI should be evaluated as a profile of acoustic, expressive, interactional, and robustness capabilities rather than by a single aggregate score.

This paper describes DS@GT ARC's submission to the CLEF 2026 LongEval Task 4 on Retrieval-Augmented Generation (RAG). In this submission, we examine a divergence between traditional natural language evaluation metrics and citation integrity as applied to RAG QA systems. We evaluate a corrective pipeline using Corrective RAG (CRAG) and CiteFix against baseline and frontier model benchmark RAG QA scores. While frontier models maximized answer relevance and fluency scores, our RAGAs LLM-as-judge diagnostics indicate that frontier models would correctly identify relevant documents without using their context in answer generation. Conversely, by filtering chunks pre-generation and enforcing strict entailment of generated claims to the cited material post-generation, our corrective pipeline marginally improved citation faithfulness and answer grounding. We propose that evaluation of trustworthy RAG QA requires metrics that reward strict answer grounding.

Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-only evaluation hides a key limitation: these models fail to encode negated sound concepts, mapping affirmative and negated captions to nearly identical representations. To expose this blind spot, we introduce NegEval-Audio, a framework that converts existing datasets into two negation-aware tasks, Retrieval-Neg and Multiple-Choice Negation (MCQ-Neg), to probe whether models distinguish present from absent events. On AudioCaps and Clotho, performance degrades sharply under negation, with negation-type MCQ accuracy falling far below chance, and the failure persists even for a recent multimodal LLM-based embedding model. While a training-free steering method improves MCQ-Neg, it yields marginal gains for Retrieval-Neg. This indicates that affirmation bias is a fundamental flaw in the representation geometry, necessitating explicit negation-aware training objectives.

Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these systems behave naturally in conversations, where timing, turn-taking, prosody, interpersonal stance, language and dialect consistency, and relationship-aware appropriateness jointly shape perceived quality. We introduce SPEARBench, a benchmark for evaluating naturalness in speech-to-speech language models from question-answer interactions. SPEARBench constructs controlled dialogue prompts from the Seamless Interaction corpus, runs inference across multiple models, and evaluates generated answers using a multidimensional protocol that covers response latency, interruptions, speech quality, ASR robustness, language and dialect consistency, emotional naturalness, interpersonal stance, and explainable distributional baselines. The benchmark includes original human answers as a reference condition and reports results for several contemporary models. Results show that current models can achieve high signal-level quality and low ASR error while still differing from human conversational behavior in latency, overlap, dialect preservation, emotional adaptation, and interpersonal stance dynamics.

Multi-step symbolic reasoning is essential for robust financial analysis, yet most benchmarks neglect intermediate reasoning steps. FINCHAIN introduced verifiable Chain-of-Thought (CoT) evaluation but is limited to English. FINESSE-Bench includes a Russian block but relies on multiple-choice questions without step-level supervision. We present RusFinChain, the first Russian-language symbolic benchmark for verifiable CoT reasoning in finance. It spans 17 domains, 172 topics, and comprises 5,280 parameterized examples from executable Python templates, ensuring contamination-free evaluation. Each example includes a gold-standard reasoning chain with intermediate numeric values for automatic verification. We also introduce enhanced metrics: Fuzzy Numeric Alignment and Soft-Attention Alignment. We evaluate 8 open-weight LLMs on a stratified sample, generating 8,100 responses. Results reveal a substantial reasoning gap: models achieve Hard F1 of ~0.65 for step alignment, but only ~29% of final answers are correct. Our fuzzy and soft metrics show stronger correlation with final-answer correctness (Spearman rho approx 0.48) than the original ChainEval (rho approx 0.38-0.46), demonstrating superior diagnostic power. We release dataset, code, and evaluation framework to foster verifiable financial AI for the Russian-speaking community.

Text embeddings are standard for semantic similarity tasks, yet their evaluation remains an open challenge. Current benchmarks are static, cover only a limited set of languages, are often domain-specific, susceptible to overfitting, and poorly representative of low-resource languages. To address these limitations, we introduce ALEE, a framework that extends Sentence Smith (Li et al., 2025) to the cross-lingual and paragraph level. ALEE uses Abstract Meaning Representations (AMR) to generate English minimal pairs with controlled, fine-grained semantic shifts, which are paired with translations in target languages. This approach enables targeted diagnostics for models in any language with English parallel data. We conduct a large-scale empirical study across a diverse set of embedding models and 275+ languages spanning three parallel datasets. On ALEE, performance varies substantially across languages, text lengths, and linguistic phenomena, exposing persistent gaps in cross-lingual semantic representation that track language prevalence in training resources and subword tokenization. We release ALEE at https://github.com/Andrian0s/any-lang-embed-eval

Earnings announcements release two types of information sequentially: quantitative surprise (numeric earnings-per-share (EPS)/revenue versus analyst estimate) arrives first in press releases and financial news, processed by algorithmic traders within minutes; qualitative language (management tone, guidance, question-and-answer (Q&A) credibility) arrives 30-90 min later in the earnings conference call transcript (ECT), requiring human interpretation overnight. Financial economists have studied quantitative surprise for 50 years; natural language processing (NLP) researchers have studied qualitative ECT signals for a decade. Despite studying the same event, the two communities used incompatible frameworks: different targets (return vs. volatility), trading setups (long top-decile and short bottom-decile vs. trade-all), and metrics (return spread between top and bottom 20% (Q5-Q1) vs. mean squared error (MSE)), making direct comparison and connection challenging. We bridge these communities with EarningsInOne, the first corpus aligning earnings news, ECTs, and intraday and next-day prices across SP 1500 (broad U.S. equity universe, 2022-2025). Applying unified trading and evaluation tools to both signal types, we confirm a clean speed separation, fast numbers, slow language: quantitative surprise peaks at announcement and is largely eliminated by the next market open; qualitative ECT sentiment peaks on the next trading day, real and tradeable, but hidden under prior transcript-based evaluation that optimised sign-agnostic volatility with pointwise MSE.

The standard way to compare two text embeddings is cosine similarity. Scattered studies report that a different metric does better, but never pin down the geometric condition that decides when, or why. We settle both with a comprehensive empirical study: nineteen parameter-free similarity metrics on nineteen encoders, from compact sentence transformers up to seven-billion-parameter large language models, across seven datasets. The answer is geometric. When an encoder spreads its variance evenly across directions, cosine is the best parameter-free choice and no other metric helps by a usable margin. When the variance concentrates into a few dominant directions, a property known as anisotropy, rank-based and L1-type metrics beat cosine by a clear margin. The absolute gain is modest, but because cosine starts low on these encoders it is a sizable relative improvement, around twenty percent on average and largest where cosine is weakest. What decides this is the geometry of the embedding space, not how the model was trained: where the two disagree, the metric follows the geometry. One number, the fraction of variance held by the single most dominant dimension, predicts how much the alternatives help across all nineteen encoders, with a rank correlation of 0.86 and a linear correlation of 0.95. To test this as the cause rather than a correlate, we project out the dominant directions: cosine recovers and the advantage of the other metrics nearly vanishes, but only on the encoders that were anisotropic to begin with. The effect is directional, not magnitude based, since it survives normalizing every vector to unit length. Among parameter-free metrics, then, cosine is the right tool wherever an encoder is well spread, which includes the fine-tuned embedders commonly deployed for retrieval, and we give a one-number diagnostic for when it is not.

Popular ASR test sets adopt inconsistent conventions for numbers, disfluencies, entities, and casing, while standard normalizers erase the format distinctions users care about. Current benchmarks therefore cannot measure whether a model follows user preferences for output style. We introduce PreferenceASR, a test set evaluating ASR systems on their ability to follow natural-language preference instructions across four categories: normalization, entities, disfluencies, and case. Built from seven open-source corpora via a two-stage LLM-assisted pipeline with human verification, it is evaluated with a preference-aware normalizer that selectively skips steps matching the active instruction. Benchmarking four models shows rankings shift across preference types, exposing quality differences traditional evaluation obscures. We publicly release the dataset.

Recent advancements in generative artificial intelligence (AI) and large language models (LLMs) have shown significant promise in automating complex reasoning, summarization, and question-answering tasks. However, the effectiveness of general-purpose LLMs in specialized engineering domains remains limited due to insufficient exposure to technical standards, engineering terminology, and domain-specific semantics. This study proposes a systematic approach to developing a customized generative AI agent for transportation engineering applications. A curated corpus of U.S. transportation manuals, design guidelines, and regulatory documents is used to conduct continued pretraining of six state-of-the-art LLMs through a unified low-rank adaptation (LoRA) framework. The training process is monitored to ensure convergence and model stability. Performance is evaluated using standard natural language processing metrics, including BLEU-4 and ROUGE, with Qwen2.5-7B and LLaMA-3.1-8B demonstrating the highest domain alignment and response quality. Results validate the effectiveness of LoRA-based adaptation in improving LLM performance on technical content interpretation and context-specific reasoning. This work contributes a reproducible development framework for constructing domain-specialized generative AI agents, supporting broader deployment in transportation research, design, planning, and policy analysis.

This paper describes team HSA_CORAL's submission to the FinCausal 2026 shared task on extracting cause-effect relations from financial narratives via extractive question answering in English and Spanish. We compare three modeling families: (i) encoder-only token tagging with multilingual BERT, (ii) encoder-decoder generation with multilingual BART, and (iii) decoder-only LLMs (Llama 3.1 and GPT variants) using prompt refinement, few-shot demonstrations, and supervised fine-tuning. Across settings, prompting and few-shot examples yield competitive performance, while supervised fine-tuning provides the largest gains. Our best system, GPT-4.1 Mini fine-tuned on combined English and Spanish training data, achieves a tied highest score on the English subtask (score 4.8140) and ranks third on Spanish (score 4.7753) under the shared task's LLM-as-a-judge metric. Overall, the results highlight the value of task-specific adaptation and multilingual fine-tuning for cross-lingual transfer in financial causality QA.

Tokenization is a foundational step in NLP pipelines, yet standard evaluation metrics such as fertility rate fail to capture morphological correctness for agglutinative languages. We present QuechuaTok, a systematic benchmark comparing four tokenization strategies - BPE, Unigram LM, WordPiece, and a morphology-aware PRPE tokenizer - for Southern Quechua (quz), a low-resource agglutinative language spoken by 8-10 million people in South America. Using a 200k-sentence corpus and the SQUOIA finite-state morphological analyzer (Rios, 2016) as silver standard, we evaluate three metrics: fertility rate, OOV rate, and morphological boundary accuracy (MorphAcc). Our results show that BPE achieves the lowest fertility rate (1.636 at 16k vocab) by memorizing surface word forms, while achieving only 6.67% MorphAcc. PRPE achieves 83.33% MorphAcc - the highest of all systems - demonstrating that fertility rate alone is insufficient to evaluate tokenizers for agglutinative languages. All code and models are publicly available at kaggle.com/code/macmaky/quechuatok

As retrieval systems scale, effective and efficient reranking becomes increasingly important. However, most existing encoder- and decoder-based rerankers jointly process every query--passage pair, tightly coupling their online computation and limiting deployment efficiency and flexibility. We present KaLM-Reranker-V1, a fast but not late-interaction FBNL reranker that decouples query and passage computation while retaining expressive relevance modeling. Built on an encoder--decoder architecture, KaLM-Reranker-V1 pre-encodes passages using Matryoshka embedding pooling, while its decoder models system and user instructions together with query intent; cross-attention then captures fine-grained relevance between the resulting query context and passage representations. Together, these designs offer four key advantages: (i) efficiency from offline passage encoding, (ii) expressiveness from cross-attention, (iii) compactness from Matryoshka embedding pooling, and (iv) test-time compute through an adjustable compute budget. We instantiate KaLM-Reranker-V1 in three sizes, Nano, Small, and Large, with 0.27B, 1B, and 4B activated parameters, respectively. Extensive experiments on BEIR, MIRACL, and LMEB demonstrate strong reranking performance with superior efficiency. On BEIR and MIRACL, our models achieve competitive performance in multi-domain and multilingual reranking, on par with strong industrial rerankers such as the Qwen3/BGE-Reranker series. On LMEB-Dialogue, a compact embedding model paired with our Nano reranker, which has only 0.27B activated parameters, remains competitive with 7--12B embedding models. Data and models are available at https://huggingface.co/collections/KaLM-Embedding/lychee-kalm-reranker-and-jev.

Existing financial-NLP benchmarks mostly evaluate prepared artifacts such as filings, tables, or extracted values. Real accounting begins earlier: source documents must be reconciled into cited journal entries, aggregated into a balance sheet, and checked for contradictions. We introduce FinBalance, a multi-document accounting reconciliation benchmark built from source-document bundles across eight industries, three period types, and five difficulty levels. Human-authored business scenarios, accounting policies, tax/FX treatments, document schemas, distractors, and inconsistency templates are composed by a deterministic generator whose ledger produces journal entries,balance sheets, and 23 inconsistency-code labels. On a 710-record evaluation split, six contemporary LLMs reach at most 46% exact final-balance-sheet accuracy. Four models show a 26-41 pp gap between BS_exact, the model's reported balance sheet, and BS_recon, the balance sheet obtained by replaying its entries through our ledger. Models often recover numerically plausible entries but fail to bind them to supporting documents and aggregate them consistently. Citation-pressure prompting barely changes document-linking errors, while ledger-feedback ablations substantially improve reported balance sheets and expose inconsistency-detection trade-offs. Expert finance reviewers validate the benchmark design and labels.

Socio-cultural stereotypical bias is an important consideration in the development and deployment of NLP systems. It is however often considered only at the national level, despite rich subnational socio-cultural structures. We present AmchiBias, the first benchmark for measuring socio-cultural stereotypical bias for the Indian state of Goa with its unique historically multicultural setting. It covers various Goan identity groups and comprises 313 minimal pairs across eight sociodemographic dimensions in both English and Devanagari Konkani. We then evaluate stereotypical bias in five multilingual encoder models on this benchmark. We find near-chance scores in Konkani, reflecting language incompetence for general multilingual models and a lack of Goan cultural competence for Indian language models. Queried in English, models with a stronger Indian language coverage show higher bias for pan-Indian groups than hyperlocal Goan groups. This suggests the English signal reflects pan-Indian pretraining associations rather than genuine Goan cultural knowledge. Our findings highlight a critical gap in low-resource multilingual NLP evaluation for hyperlocal community identities.

Language models, as multi-task learners, acquire a wide range of abilities during training. A fundamental question is how much task-specific data is needed to learn a given task. Answering this for natural language is difficult: tasks are hard to delineate and can confound one another. To rigorously investigate the relationship between data frequency and learnability, we turn to a controlled setting using formal languages induced from probabilistic finite automata. These serve as a methodological testbed to demonstrate that standard correlational evaluation practices are inherently flawed. To enable causal analysis, we introduce the binning semiring, an algebraic object that lets us control how often a targeted property occurs in a sampled corpus. We formulate the experimental pipeline as a causal graphical model and derive decomposed Kullback-Leibler divergence metrics to measure the learnability of specific sub-tasks. Our experiments show that evaluating learnability without causal intervention leads to incorrect conclusions due to confounders in correlational analysis, and serve as a warning about correlational pitfalls in natural-language settings.

Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but silently drops nested exceptions or counter-exceptions, producing outputs that appear compliant yet break on important edge cases. Although such failures are often framed as an agentic-systems problem, the underlying bottleneck is statutory and policy understanding, a capability typically studied in legal NLP. However, most existing legal NLP benchmarks emphasize end-task outcomes, which can overlook the structural omissions that cause SSO. To diagnose and mitigate SSO, we introduce NormBench, a benchmark of 2,290 provisions spanning Chinese (laws and local policies), English (U.S. tax law, GDPR, and corporate policies), and cross-lingual settings, designed for defeasible scope parsing: identifying precisely which clause overrides which. NormBench uses Span-Grounded Deontic Trees (SG-DT), a compiler-style intermediate representation that anchors every logical branch to source spans and requires explicit exclusion guards, enabling deterministic compilation and audit. Evaluations of frontier LLMs reveal two recurring pathologies: (1) Recursion Decay, where performance drops sharply as defeater depth increases, and (2) an Auditability Trap, where models retrieve relevant spans but fail to assemble correct control flow. Using SG-DT as a constrained intermediate output improves whole-tree fidelity and defeater recovery, and downstream experiments show that its utility is mechanism-specific: gains concentrate on exception-active, SSO-prone cases, while aggregate accuracy can be mixed when the added structure is unnecessary or parser fidelity is low.

Evaluating the quality of automatically generated keyphrases remains a complex challenge. Traditional metrics either rely on exact lexical matching or consider semantic similarity while ignoring prediction ranking, both of which misalign with how humans judge informativeness and relevance. We introduce Semantic R-Precision (SemR-p), a novel evaluation metric that integrates semantic similarity into the rank-aware R-Precision framework. Designed from a human-centric perspective and inspired by Information Retrieval metrics, SemR-p rewards semantically relevant keyphrases that appear early in the output list. We conducted extensive analyses to assess its semantic sensitivity, ranking awareness, and discriminative power across models and datasets. The results suggest that SemR-p offers a complementary lens for evaluating keyphrase predictions, helping to better reflect user-centred notions of relevance alongside traditional lexical and semantic matching metrics.

High-throughput microscopy generates large, structured datasets capturing cellular responses to pharmacological perturbations, but accessing these datasets typically requires SQL expertise. Large language models offer a natural-language alternative, yet their tendency to hallucinate raises concerns about result reliability . We present SANE Schema-Aware Natural-language Evaluation, a novel paradigm for domain-specific text-to-SQL evaluation: schema-grounded, automatically generated benchmarks tied to real and specific experimental structure. SANE makes evaluation more scalable, systematic, and reproducible. Using SANE, we evaluate a few-shot large language model and show that, under constrained schemas with structured prompting and guardrails, accurate query generation is achievable without any model training or fine-tuning. Most failures stem from ambiguous or underspecified inputs and manifest as overly cautious clarification requests or answers to queries that should first be disambiguated, rather than incorrect SQL generation. These results indicate that few-shot large language models can provide reliable database access in well-defined domains when combined with schema-aware prompting.

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.

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.

Legal NLP benchmarks overwhelmingly evaluate a single language or aggregate tasks that differ fundamentally across jurisdictions, making cross-lingual comparison impossible. We introduce Multi-Legal-Bench, the first cross-jurisdictional legal benchmark that evaluates identical tasks across six countries (Ukraine, France, Netherlands, Poland, Czech Republic, Lithuania), four language families, and 134 million court decisions. The benchmark defines five tasks court-type classification, judgment form classification, case-outcome prediction, legal norm extraction, and cause category prediction mapped to structured metadata from national court registries, forming a deliberately sparse 5x6 task-jurisdiction matrix (20 of 30 cells filled). We evaluate 7 frontier LLMs under zero-shot and 3-shot prompting via AWS Bedrock, with 4 additional small/medium models (3-12B) for scaling analysis. Our results reveal that: (1) task-dependent few-shot effects discovered in Ukrainian replicate across all jurisdictions; (2) no single model dominates any language rankings shift with both task and jurisdiction; (3) cross-lingual few-shot transfer does not follow language proximity: UA->FR (Romance, -2.1 pp) transfers better than UA->PL (Slavic, -13.7 pp), with label-set alignment predicting transfer quality better than language family; and (4) tokenizer fertility, despite a 2.3x spread, does not significantly predict cross-lingual accuracy (r=-0.27, p=0.14), suggesting that model architecture and pretraining data dominate tokenizer efficiency. We release all data, prompts, and model predictions.

Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We introduce UA-Legal-Bench, a five-task benchmark for evaluating large language models on Ukrainian legal reasoning, built from the Unified State Register of Court Decisions (EDRSR) -- one of the world's largest open judicial corpora (99.5 million decisions). The benchmark comprises: (1) case-type classification (4 classes, n=2,000), (2) judgment form classification (4 classes, n=2,000), (3) case-outcome prediction (6 classes, n=800), (4) legal norm extraction (n=1,794), and (5) cause category prediction (22 classes, n=1,871). We evaluate 11 LLMs (3B--675B) from five families under zero-shot and 3-shot prompting via AWS Bedrock with 158K API calls. Our results reveal sharply task-dependent few-shot effects: few-shot prompting improves judgment form classification by up to +38.6 pp but has mixed effects on outcome prediction. We show that accuracy is misleading on imbalanced legal tasks: the model with highest COP accuracy (62%) is a majority-class predictor (macro-F1: 23%), while the genuinely best model scores only 44% macro-F1. Within-family scaling analysis reveals that 8B models can match frontier performance on surface-level tasks but scaling thresholds vary dramatically across families. We release all data, prompts, and model predictions.

A retrieval-augmented generation (RAG) system deployed over a multi-author institutional corpus can give a different answer to the same question depending on which source it retrieves -- a failure mode the dominant single-gold-answer paradigm cannot diagnose. We argue that source-dependence is a missing axis of NLP evaluation, and that auditing it means shifting the unit of evaluation from answer correctness to the inter-source relationship. We make this concrete in transplant patient education, where institutional sources demonstrably disagree, releasing three artefacts: TransplantQA, a benchmark of real patient questions, each answered by grounding generation in multiple institutional handbooks as candidate sources; HERO-QA, a hierarchical retrieval strategy that grounds and audits each answer; and a structured-output judge that scores inter-source relationships on a validated 5-label taxonomy. At scale, better retrieval reveals far more disagreement than prior estimates suggested -- understating its prevalence, not its intensity. The framework is domain-agnostic and transfers to legal and educational RAG: measuring source-dependence is a responsibility for deployed multi-source NLP generally.

Fine-tuning large-scale pre-trained models is a recent prevalent paradigm for adapting general representations to specialized tasks. However, when a new version of a pre-trained model becomes available, expertise acquired through fine-tuning cannot be directly reused because it is tied to the parameterization of the original model, requiring another costly fine-tuning. To address this inefficiency, recent work uses task vectors, defined as the parameter difference between a fine-tuned model and its base model, to transfer expertise across models. While existing methods bridge disparate models by matching activations or gradients, a significant performance gap remains relative to direct fine-tuning, suggesting that these partial correspondences are insufficient. In this work, instead of viewing a task vector merely as a parameter offset, we revisit the formation of task vectors and show that they can be derived as accumulated bilinear interactions between input-side activations and output-side gradients. Motivated by this observation, we formulate task-vector transfer as a dual-space alignment problem and propose BiCo, a training-free framework for transferring task vectors through Bilinear Coordinate alignment. BiCo estimates orthogonal Procrustes mappings in both spaces using a single forward-backward pass on a small calibration set, without any parameter update. Across extensive computer vision and natural language processing benchmarks, BiCo consistently outperforms existing transfer methods across models that differ in width, depth, and pre-training configuration.

Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g., ROUGE) and embedding-based measures (e.g., BERTScore), often misjudge semantic similarity of documents. Our study shows that both token-overlap metrics and embedding-based metrics routinely assign nearly identical scores to texts that directly contradict each other, thereby potentially masking fundamental errors. We introduce MATCHA, an automatic metric that jointly rewards semantic agreement with a reference and penalizes contradictions. MATCHA employs a dual-view perspective that measures (i) proximity to the gold text and (ii) distance from an adversarially generated counterfactual contradiction. In eight public benchmarks, MATCHA outperforms popular metrics, compared with human annotations on question-answering, image caption generation, natural language inference, summarization, and semantic textual similarity tasks. On the TruthfulQA dataset (i.e., a dataset without a training set, where no embedding-based metrics could locally train on), this improvement in terms of matching texts with a reference reaches 18.38% over ROUGE-L and 20.82% over BERTScore. Both quantitative comparison and qualitative human assessments confirm the efficacy and validity of MATCHA and uncover fundamental weaknesses in pre-existing metrics. Compared with 23 embedding models, including top state-of-the-art ones, used as a metric similar to BERTScore, MATCHA remains the most accurate in distinguishing correct from incorrect statements solely based on a reference. Our code and metric are publicly available (https://github.com/Siran-Li/MATCHA).

Computing legal indicators from normative texts is a key task in legal monitoring and policy evaluation, but presents significant challenges due to the complexity, scale, and interpretive nature of legal language, as well as the variability in available document quality. Existing natural language processing techniques and generative models can assist in legal analysis, but often suffer from high risk of hallucinations and lack the interpretability and evidence grounding required for reliable indicator computation. This paper presents N2I-RAG (From Norms to Indicators), an agentic retrieval-augmented generation framework designed to automate the computation of legal indicators in a transparent and traceable way. We integrate adaptive retrieval, llm-based agents, and validation mechanisms in a modular pipeline, where each component performs a defined role in filtering, retrieving, and assessing evidence, and in producing binary legal outcomes linked to identifiable legal provisions. The framework emphasizes traceability by requiring explicit explanations of intermediate decisions and final indicator assignments. We evaluate N2I-RAG using an in-house constructed French marine environmental law corpus that includes both scanned and digital sources. Comparative experiments with multiple language model families demonstrate that the proposed approach consistently outperforms baseline systems, and generalizes well when tested on 2 different bans. The results indicate that agentic retrieval-augmented generation can bridge open-text legal language and standardized indicator computation, offering a foundation for transparent and scalable legal observatories.

Natural language conveys information at varying levels of granularity, from fine-grained references to broad descriptions. While granularity is fundamental to human communication, existing measures mostly capture surface detail or sentence specificity. We introduce Granuscore, a reference-free measure of granularity that leverages structural properties of a hierarchical embedding space. Granuscore reliably recovers hierarchical orderings on the Granola-EQ dataset and captures expected differences in granularity across discourse contexts. Across domains, we further show that Granuscore explains non-linear variation in sentence specificity beyond sentence length. Finally, we apply Granuscore to four question-answering benchmarks and analyze how granularity differs for questions, gold answers, and model outputs across response outcomes. The analysis reveals consistent differences in model behavior and provides a principled lens for characterizing the difficulty of QA datasets. Together, the results position Granuscore as a scalable, broadly applicable tool for analyzing granularity in text.

Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuring how language is perceived rather than what speakers have committed to in the market. We introduce StakeBench, an evaluation framework for language understanding grounded in market commitment. StakeBench links 560,876 comments from 2,261 resolved markets to verified position, action, and market-odds records across Polymarket and Manifold. Supervision is derived from observable market behavior. Position sides, post-comment trading actions, and market-odds trajectories replace human annotation. Four diagnostic tasks test whether models detect market commitment, identify the revealed side, anticipate future action, and perform collective odds projection. Three commitment-aware metrics measure alignment with revealed preferences rather than perceived sentiment. Validity audits and explicit interpretation boundaries help distinguish observable commitment signals from latent belief and causal market-odds impact. Across 15 LLMs and 18 topics and platform settings, models partially recover position-side signals, with Directed Accuracy from 0.506 to 0.599, but show structural failures on later tasks. Ten of the fifteen models collapse to one or two action labels in future action anticipation, and no model consistently improves on the naive odds-direction baseline in collective odds projection. Model scale is not correlated with performance, finance-domain tuning does not improve revealed-side identification, and platform incentives strongly shape higher-order results. StakeBench is packaged with evaluation code and dataset under CC-BY 4.0.

Tokenizer fertility the number of tokens per word imposes a hidden cost on non-English NLP. We measure fertility for ten foundation models across 25 European languages on parallel text, producing the first controlled tokenizer tax map for the continent. The tax spans 2.5x from English (1.2 tokens/word) to Greek/Maltese (~3.1), following a clear hierarchy: Romance (1.5-1.7), Germanic (1.7-1.9), Slavic (2.2-2.5), Uralic/Baltic (2.7-3.0). Ukrainian (2.7) pays 15-18% more than cognate Slavic languages, reflecting underrepresentation in pre-training data. Fertility rankings are domain-invariant across three text registers (rho > 0.97). A subword analysis reveals that high-fertility tokenizers fragment morphological boundaries rather than preserving them. Cross-lingual few-shot evaluation on four Slavic languages shows that few-shot effects are model-intrinsic, not language-dependent. We release all measurements as a public dataset.

Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tuning four transformer encoders -- XLM-RoBERTa (base and large) and their legal-domain variants -- on Ukrainian court decisions from three temporal epochs defined by geopolitical disruptions: pre-war (2008-2013), hybrid war (2014-2021), and full-scale invasion (2022-2026). Each model is trained on one epoch and evaluated on all three, producing a 3x3 cross-temporal generalization matrix. Four findings emerge. (1) Forward degradation is severe: models trained on pre-war data lose up to 27.2 percentage points of macro-F1 when applied to full-scale invasion era decisions. (2) The degradation is asymmetric: backward transfer (full-scale to pre-war) is substantially more robust than forward transfer, consistent with the hypothesis that legal language is additive. (3) Legal-domain pretraining (Legal-XLM-R) does not improve absolute performance but reduces forward degradation magnitude and asymmetry. (4) Chronological continual learning eliminates catastrophic forgetting for general XLM-R: pre-war knowledge is fully retained (+1.8 to +6.2 pp) while full-scale performance gains +16.5 to +19.0 pp; reverse-chronological training causes severe forgetting. Cross-jurisdictional pretraining on Swiss Judgment Prediction data improves absolute performance but does not reduce temporal degradation magnitude, confirming that temporal drift is an intrinsic property of legal language evolution. The dataset (428K decisions across three epochs) is publicly available as a LEXTREME contribution.

Idioms pose a fundamental challenge for language models, as their meaning cannot be inferred from surface form alone. Understanding such expressions, therefore, requires semantic abstraction beyond lexical overlap. We introduce IdioLink, a retrieval benchmark designed to test whether models can link idiomatic expressions to conceptually equivalent meanings expressed in literal or paraphrased forms. IdioLink comprises 10,700 documents and 2,140 queries, spanning 107 idioms with both literal and figurative uses. Each document and query is annotated with spans that convey the core meaning. Evaluating strong embedding baselines (e.g., BGE, E5, Contriever, and Qwen), we show that current models struggle to retrieve equivalent meanings across divergent surface realizations, relying instead on topical and shallow semantic cues. IdioLink exposes key gaps in idiom-aware semantic retrieval and provides a challenging testbed for future models.

The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-stake domains such as law, retrieval-augmented generation (RAG) is commonly used to mitigate hallucinations in generated responses. Nonetheless, prior work shows that RAG systems, whether general-purpose or legal-specific, still hallucinate at varying rates, making fine-grained evaluation essential. Despite the need, existing evaluation frameworks for legal RAG systems lack the granularity required to provide detailed analysis of retrieval and generation performance separately. Moreover, current benchmarks are largely English-only and centered on legal expert queries, overlooking non-expert needs. We introduce ClaimRAG-LAW, a comprehensive dataset for legal RAG that supports French and English, targets both experts and non-experts, and includes diverse question types reflecting realistic scenarios. We further apply a fine-grained evaluation framework of state-of-the-art legal RAG systems, revealing limitations in retrieval, generation, and claim-level analysis in the legal domain.

Over the past decade, low-resource natural language processing (NLP) has experienced explosive growth, propelled by cross-lingual transfer, massively multilingual models, and the rapid proliferation of benchmarks. Yet this apparent progress masks a critical, insufficiently examined tension: the deep sociolinguistic expertise required to evaluate increasingly complex generative systems is severely strained, inequitably distributed, and structurally marginalised. We present a critical narrative survey of low-resource NLP evaluation (2014-present), tracing its evolution across three phases: early heuristic optimism, the illusions of top-down benchmark scaling, and the current era of generative bottlenecks. We conceptualise the Annotation Scarcity Paradox, the structural friction arising when the technical capacity to scale models vastly outpaces the sovereign human infrastructure required to authentically evaluate them. By examining extractive data pipelines, undercompensated ``ghost work'', and language data flaring, we argue that this paradox threatens the epistemic validity of reported progress. We survey emerging responses -- including data augmentation, model-based evaluation, participatory curation, and annotation-efficient approaches via item response theory and active learning -- and assess their equity and validity trade-offs. We close with a practitioner call to action, arguing that overcoming this bottleneck requires a paradigm shift from transactional data extraction to relational, community-embedded evaluation rooted in epistemic governance, data sovereignty, and shared ownership.

Multilingual NLP often relies on dataset counts from centralized catalogues to characterize which languages are resource-rich or resource-poor. However, these catalogues record only one layer of dataset visibility: what has been registered or institutionally distributed. They do not necessarily reflect which datasets are created, cited, or reused in the research literature. To examine this gap, we combine a catalogue-based baseline with literature-backed evidence of dataset circulation. We introduce the Resource Density Index (RDI), defined as the number of catalogued datasets per one million speakers, and compute it for the 200 most widely spoken languages in Ethnologue. Among them, 118 languages (59%) have an average RDI of zero across the LRE Map and the Linguistic Data Consortium (LDC), and another 23 fall below 0.1, corresponding to at most one catalogued dataset per ten million speakers. We then apply an LLM-assisted citation-mining pipeline over the Semantic Scholar corpus to these 141 low-visibility languages. After manual validation and consolidation, we identify 609 unique datasets across 53 languages, of which 356 remain openly accessible through working public links. These results reveal a substantial visibility gap: many large-speaker languages appear data-poor in catalogue records yet show clear evidence of dataset activity in the research literature. Our findings suggest that multilingual data scarcity should be understood not only as a production problem, but also as a question of documentation, discoverability, and long-term accessibility. Code and data are publicly available at (https://github.com/zhiyintan/dataset-visibility-asymmetry).

Tokenizer fertility varies 1.6x across foundation models on Ukrainian legal text, yet this cost-critical dimension is absent from model selection practice. We benchmark seven models from five providers on 273 validated court decisions from Ukraine's state registry (EDRSR), measuring tokenizer fertility and zero-shot performance on three tasks. Four findings emerge. (1) Qwen 3 models consume 60% more tokens than Llama-family models on identical input, making tokenizer analysis a prerequisite for cost-efficient deployment. (2) NVIDIA Nemotron Super 3 (120B) achieves the highest composite score (83.1), outperforming Mistral Large 3 (5.6x more total parameters) at one-third the API cost model scale is a poor proxy for domain performance. (3) Few-shot prompting degrades performance by up to 26 percentage points; stratified and prompt-sensitivity ablations confirm this is intrinsic to Ukrainian-language demonstrations, not an artifact of example selection. (4) A cross-temporal generalization experiment reveals that classifiers trained on pre-war court ecisions (2008-2013) lose 27.9 percentage points when applied to full-scale invasion era decisions (2022-2026), with a pronounced forward-backward asymmetry: newer models transfer backward (+14.6 pp above forward transfer), but older models fail catastrophically on wartime legal language. For practitioners: tokenizer analysis should precede model selection, and zero-shot is a more reliable default than few-shot for morphologically rich languages. To support reproducibility and address the absence of Ukrainian from legal NLP benchmarks, we release a public dataset of 14,452 court decisions spanning 2008-2026, annotated with seven outcome labels across three temporal epochs that capture the impact of armed conflict on judicial proceedings.

While LLMs are increasingly used in commercial services, they pose privacy risks such as leakage of sensitive personally identifiable information (PII). For LLMs trained on multilingual corpora, Multilingual Machine Unlearning (MMU) aims to remove information across multiple languages. However, prior MMU evaluations fail to capture such cross-linguistic distribution of information, being largely limited to direct extensions of per-language evaluation protocols. To this end, we propose two metrics to evaluate the information spread across languages: the Knowledge Separability Score (KSS) and the Knowledge Persistence Score (KPS). KSS measures the overall unlearning quality across multiple languages, while KPS more specifically aims to assess consistent removal of information among different language pairs. We evaluated various unlearning methods in the multilingual setting with these metrics and conducted comprehensive analyses. Through our investigation, we provide insights into unique phenomena exclusive to MMU and offer a new perspective on MMU evaluation.

We present CodeEvolve, an evolutionary framework for improving program performance and code quality with Large Language Models (LLMs). CodeEvolve extends OpenEvolve with runtime-guided target selection, Monte Carlo Tree Search (MCTS), automated code refinement, and language-specific evaluation pipelines for Java and Salesforce Apex. The system uses Java Flight Recorder (JFR) profiles to build weighted component graphs and select optimization targets that account for most execution cost, reducing reliance on manual bottleneck identification. For each target, CodeEvolve generates candidate edits, evaluates them through build validation, unit tests, performance checks, static analysis, and LLM-based review, and retains only variants that preserve functional correctness. Across real-world optimization tasks, CodeEvolve improves performance and code metrics while maintaining correctness. On a large enterprise Java codebase, it achieves an average speedup of 15.22$\times$ across seven hotspot functions and outperforms single-pass LLM optimization on five of them. An ablation study on Apex optimization shows that the full MCTS-augmented configuration produces 19.5 valid programs out of 20 on average, indicating that search, filtering, and refinement each contribute to more reliable optimization.

Large language models perform well on high-resource pairs but are less reliable for Japanese-Chinese sentences containing noun-modifying clause constructions (NMCCs). This study evaluates a retrieval-augmented generation RAG+Prompt translation system that integrates linguistic analysis, embedding-based retrieval, prompt construction, and LLM generation without modifying the base model. The analysis module outputs A1 (inner vs. outer NMCC) and A2 (risk predictions: lexical choice/NMCC handling/word order/style/register); top-k = 5 similar Ja-Zh examples (L2 distance) and A1/A2 are inserted into an enhanced prompt. Using GPT-4o and a 66-sentence test set, we compare six knowledge-base sizes (0/100/200/500/1,000/2,000). Macro-averaged sentence-level BLEU (1-4-gram with brevity penalty; cased; Chinese at the character level) is the sole metric. Mean BLEU increases from 24.28 at 0 (RAG disabled) to 29.96 at 2,000 (+5.68; +23.4%). The upward trend holds across sizes, with larger knowledge bases yielding higher scores. We conclude that the RAG+Prompt translation system improves Ja-Zh translation of sentences containing NMCCs in an interpretable and auditable manner. Limitations include one base model, one metric, and reliance on published texts and commercial APIs; future work will broaden genres, language pairs, and evaluation metrics.

How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss discourse structure, while embeddings conflate local coherence with global organization. No existing framework maps these techniques onto the hierarchical processes through which narratives are constructed. Here we introduce a three-level framework - micro-level lexical features, meso-level semantic embeddings, and macro-level LLM narrative evaluation - and show, across 830 Chinese therapeutic texts spanning depression, anxiety, and trauma, that macro-level evaluation substantially outperforms lexical and embedding features for mental health prediction. This challenges the field's emphasis on word-counting: formal structural features (Labov's story grammar, RST coherence, propositional composition) demonstrate that narrative organization per se carries predictive signal, while clinically-grounded narrative dimensions capture how psychological states are expressed through discourse. Semantic embeddings add minimal independent value but yield incremental gains in multi-level classification. By grounding computational levels in discourse processing theory, this framework identifies macro-structural organization as the primary locus of clinical signal and generates testable hypotheses for intervention design and longitudinal research.

As LLMs become credible readers of earnings calls, investor-relations Q&A, guidance, and disclosure language, supervised financial NLP benchmarks increasingly function as decision evidence for model selection and deployment. A hidden assumption is that gold labels make such evidence objective. This assumption breaks down when the benchmark ruler itself is sensitive to rubric wording, metric choice, or aggregation policy. We study this measurement risk on Japanese Financial Implicit-Commitment Recognition (JF-ICR; a pinned 253-item test split x 4 frontier LLMs x 5 rubrics x 3 temperatures x 5 ordinal metrics). Three findings follow. First, rubric wording materially changes model-assigned labels: R2--R3 agreement ranges from 70.0% to 83.4%, with the dominant movement near the +1 / 0 implicit-commitment boundary. This pattern is consistent with a pragmatic-boundary interpretation, but is not a validated linguistic-causality claim because the present rubric variants confound semantics, examples, and verbosity. Second, not every metric remains informative under the JF-ICR class distribution. Within-one accuracy is too easy because near misses receive credit and the majority class dominates; worst-class accuracy is too noisy because the rarest class has only two examples. Exact accuracy, macro-F1, and weighted \k{appa} are therefore the identifiable metrics under our operational rule. Third, ranking claims become more defensible only after this metric-identifiability audit: Bradley--Terry, Borda, and Ranked Pairs agree on the identifiable metric subset, while the full five-metric sweep produces disagreement on the closest pair. The contribution is not a new leaderboard, but a reporting discipline for supervised financial benchmarks whose gold labels exist and whose evaluation ruler still requires governance.