MATCHA: Matching Text via Contrastive Semantic Alignment

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).

Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance

Learned sparse retrieval models such as SPLADE combine the effectiveness of neural architectures with the efficiency of inverted indices. As these models assign weights to terms from a fixed vocabulary, interpretability is often touted as a major benefit of these models. However, the emergence of wacky weights, i.e., expansion terms that appear semantically unrelated to the input, limits interpretability. While prior research has anecdotally observed this phenomenon, there is a lack of systematic understanding regarding their origins, prevalence, and contribution to retrieval effectiveness. In this paper, we reproduce SPLADE-v2 to systematically investigate wacky weights across the SPLADE family of models. We present a comprehensive dissection of wacky weights, providing a formal definition of wackiness based on the lexical utility of expansion terms. Furthermore, we introduce a novel measure to compare the prevalence of these tokens across models with varying vocabularies and sparsity levels. Beyond reproducing the original SPLADE-v2, we train it with various loss functions, datasets, and backbone transformers to isolate the factors contributing to wackiness. Our results show that larger vocabularies are associated with a higher prevalence of wacky tokens, while stricter sparsity regularizers are associated with lower prevalence. Finally, we find that wacky weights are used primarily for in-domain effectiveness rather than out-of-domain generalization.

PubMed-Ophtha: An open resource for training ophthalmology vision-language models on scientific literature

Vision-language models hold considerable promise for ophthalmology, but their development depends on large-scale, high-quality image-text datasets that remain scarce. We present PubMed-Ophtha, a hierarchical dataset of 102,023 ophthalmological image-caption pairs extracted from 15,842 open-access articles in PubMed Central. Unlike existing datasets, figures are extracted directly from article PDFs at full resolution and decomposed into their constituent panels, panel identifiers, and individual images. Each image is annotated with its imaging modality -- color fundus photography, optical coherence tomography, retinal imaging, or other -- and a mark status indicating the presence of annotation marks such as arrows. Figure captions are split into panel-level subcaptions using a two-step LLM approach, achieving a mean average sentence BLEU score of 0.913 on human-annotated data. Panel and image detection models reach a mAP@0.50 of 0.909 and 0.892, respectively, and figure extraction achieves a median IoU of 0.997. To support reproducibility, we additionally release the human-annotated ground-truth data, all trained models, and the full dataset generation pipeline.

Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models

Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning beyond superficial visual cues, particularly in high-stakes domains like medicine. We evaluate four paired open-source VLMs (LLaVA vs. LLaVA-Med; Gemma vs. MedGemma) across four medical imaging tasks of increasing difficulty: brain tumor, pneumonia, skin cancer, and histopathology classification. We find that performance degrades toward near-random levels as task difficulty increases, indicating limited clinical reasoning. Medical fine-tuning provides no consistent advantage, and models are highly sensitive to prompt formulation, with minor changes causing large swings in accuracy and refusal rates. To test whether closed-form VQA suppresses latent knowledge, we introduce a description-based pipeline where models generate image descriptions that a text-only model (GPT-5.1) uses for diagnosis. This recovers a limited additional signal but remains bounded by task difficulty. Analysis of vision encoder embeddings further shows that failures stem from both weak visual representations and downstream reasoning. Overall, medical VLM performance is fragile, prompt-dependent, and not reliably improved by domain-specific fine-tuning.

When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't

Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere to their introspective reasoning are central challenges for trustworthy deployment. To study this, we introduce the Graded Color Attribution (GCA) dataset, a controlled benchmark designed to elicit decision rules and evaluate participant faithfulness to these rules. GCA consists of line drawings that vary pixel-level color coverage across three conditions: world-knowledge recolorings, counterfactual recolorings, and shapes with no color priors. Using GCA, both VLMs and human participants establish a threshold: the minimum percentage of pixels of a given color an object must have to receive that color label. We then compare these rules with their subsequent color attribution decisions. Our findings reveal that models systematically violate their own introspective rules. For example, GPT-5-mini violates its stated introspection rules in nearly 60\% of cases on objects with strong color priors. Human participants remain faithful to their stated rules, with any apparent violations being explained by a well-documented tendency to overestimate color coverage. In contrast, we find that VLMs are excellent estimators of color coverage, yet blatantly contradict their own reasoning in their final responses. Across all models and strategies for eliciting introspective rules, world-knowledge priors systematically degrade faithfulness in ways that do not mirror human cognition. Our findings challenge the view that VLM reasoning failures are difficulty-driven and suggest that VLM introspective self-knowledge is miscalibrated, with direct implications for high-stakes deployment.

When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently ignore time-sensitive evidence and conflate facts across different time-periods. In this paper, we present the first empirical study of training LLMs with an abstention ability while reasoning about temporal QA. Existing approaches such as calibration might be unreliable in capturing uncertainty in complex reasoning. We instead frame abstention as a teachable skill and introduce a pipeline that couples Chain-of-Thought (CoT) supervision with Reinforcement Learning (RL) guided by abstention-aware rewards. Our goal is to systematically analyze how different information types and training techniques affect temporal reasoning with abstention behavior in LLMs. Through extensive experiments studying various methods, we find that RL yields strong empirical gains on reasoning: a model initialized by Qwen2.5-1.5B-Instruct surpasses GPT-4o by $3.46\%$ and $5.80\%$ in Exact Match on TimeQA-Easy and Hard, respectively. Moreover, it improves the True Positive rate on unanswerable questions by $20\%$ over a pure supervised fine-tuned (SFT) variant. Beyond performance, our analysis shows that SFT induces overconfidence and harms reliability, while RL improves prediction accuracy but exhibits similar risks. Finally, by comparing implicit reasoning cues (e.g., original context, temporal sub-context, knowledge graphs) with explicit CoT supervision, we find that implicit information provides limited benefit for reasoning with abstention. Our study provides new insights into how abstention and reasoning can be jointly optimized, providing a foundation for building more reliable LLMs.

UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages

Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerable to evolving harms, cross-lingual safety failures, and cultural misalignment. Moreover, most guardian models rely on rigid, predefined safety categories that fail to generalize across diverse linguistic and sociocultural contexts. Robust safety, therefore, requires flexible, runtime-enforceable policies and benchmarks that reflect local norms, harm scenarios, and cultural expectations. We introduce UbuntuGuard, the first African policy-based safety benchmark built from adversarial queries authored by 155 domain experts across sensitive fields, including healthcare. From these expert-crafted queries, we derive context-specific safety policies and reference responses that capture culturally grounded risk signals, enabling policy-aligned evaluation of guardian models. We evaluate 13 models, comprising six general-purpose LLMs and seven guardian models across three distinct variants: static, dynamic, and multilingual. Our findings reveal that existing English-centric benchmarks overestimate real-world multilingual safety, cross-lingual transfer provides partial but insufficient coverage, and dynamic models, while better equipped to leverage policies at inference time, still struggle to fully localize African-language contexts. These findings highlight the urgent need for multilingual, culturally grounded safety benchmarks to enable the development of reliable and equitable guardian models for low-resource languages. Our code can be found online.\footnote{Code repository available at https://github.com/hemhemoh/UbuntuGuard.

Less is More: Label-Guided Summarization of Procedural and Instructional Videos

Video summarization helps turn long videos into clear, concise representations that are easier to review, document, and analyze, especially in high-stakes domains like surgical training. Prior work has progressed from using basic visual features like color, motion, and structural changes to using pre-trained vision-language models that can better understand what's happening in the video (semantics) and capture temporal flow, resulting in more context-aware video summarization. We propose a three-stage framework, PRISM: Procedural Representation via Integrated Semantic and Multimodal analysis, that produces semantically grounded video summaries. PRISM combines adaptive visual sampling, label-driven keyframe anchoring, and contextual validation using a large language model (LLM). Our method ensures that selected frames reflect meaningful and procedural transitions while filtering out generic or hallucinated content, resulting in contextually coherent summaries across both domain-specific and instructional videos. We evaluate our method on instructional and activity datasets, using reference summaries for instructional videos. Despite sampling fewer than 5% of the original frames, our summaries retain 84% semantic content while improving over baselines by as much as 33%. Our approach generalizes across procedural and domain-specific video tasks, achieving strong performance with both semantic alignment and precision.

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-counting setting, where the prompt overstates the number of objects in the image (e.g., asking a model to describe four waterlilies when only three are present). At low object counts, models often correct the overestimation, but as the number of objects increases, they increasingly conform to the prompt regardless of the discrepancy. Through mechanistic analysis of three VLMs, we identify a small set of attention heads whose ablation substantially reduces prompt-induced hallucinations (PIH) by at least 40% without additional training. Across models, PIH-heads mediate prompt copying in model-specific ways. We characterize these differences and show that PIH ablation increases correction toward visual evidence. Our findings offer insights into the internal mechanisms driving prompt-induced hallucinations, revealing model-specific differences in how these behaviors are implemented.

APP: Accelerated Path Patching with Task-Specific Pruning

Circuit discovery is a key step in many mechanistic interpretability pipelines. Current methods, such as Path Patching, are computationally expensive and have limited in-depth circuit analysis for smaller models. In this study, we propose Accelerated Path Patching (APP), a hybrid approach leveraging our novel contrastive attention head pruning method to drastically reduce the search space of circuit discovery methods. Our Contrastive-FLAP pruning algorithm uses techniques from causal mediation analysis to assign higher pruning scores to task-specific attention heads, leading to higher performing sparse models compared to traditional pruning techniques. Although Contrastive-FLAP is successful at preserving task-specific heads that existing pruning algorithms remove at low sparsity ratios, the circuits found by Contrastive-FLAP alone are too large to satisfy the minimality constraint required in circuit analysis. APP first applies Contrastive-FLAP to reduce the search space on required for circuit discovery algorithms by, on average, 56\%. Next, APP, applies traditional Path Patching on the remaining attention heads, leading to a speed up of 59.63\%-93.27\% compared to Path Patching applied to the dense model. Despite the substantial computational saving that APP provides, circuits obtained from APP exhibit substantial overlap and similar performance to previously established Path Patching circuits