This paper describes our submission to thedimABSA Shared Task (Subtask 1), whichrequires predicting continuous Valence andArousal scores for target aspects in multilin-gual reviews. We evaluate three approaches:prompting-based baselines, a multilingual en-coder model, and a decoder-only LLM withsupervised fine-tuning. Our main focus isefficient adaptation under multilingual datascarcity. We show that compact encoder anddecoder models, when properly fine-tuned,achieve strong performance across languagesand domains. To improve training stability andenforce valid predictions, we use a boundedregression formulation that maps outputs to thetarget score range. We also explore parameter-efficient fine-tuning and intermediate trainingon external affective data. Results show thatprompting-based baselines are substantiallyweaker than supervised models. The mul-tilingual encoder provides a strong and effi-cient baseline, while the best performance isachieved by a compact decoder model withparameter-efficient fine-tuning. Overall, ourfindings highlight the importance of carefulfine-tuning and training design for multilingualdimensional sentiment analysis.

Tool-augmented language models ground their responses in external tool outputs, improving reliability beyond parametric knowledge alone. However, even when the correct tool is called and returns accurate information, models may still contradict such outputs, omit critical details, or generate unsupported claims. Existing hallucination benchmarks for tool-augmented dialogue primarily focus on the tool-calling stage, evaluating whether the correct tool and arguments are selected, while overlooking errors that arise during post-tool response generation. To address this gap, we introduce , a span-level benchmark for hallucination detection in tool-augmented LLM responses, covering five fine-grained hallucination categories. Through extensive experiments with modern hallucination detectors, we show that post-tool-call hallucinations are widespread and remain challenging to detect. Our results further demonstrate that effective detection requires training on specialized tool-augmented corpora, while transfer from tool-agnostic hallucination datasets performs poorly in this setting. These findings highlight the need for dedicated benchmarks and models for reliable hallucination detection in tool-augmented language systems.

Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produces from what it discusses. We present Drift Inspector, an open-source system for measuring and exploring how a research field changes over time at the level of Atomic Contribution Claims (ACCs): decontextualized, contribution-bearing propositions an LLM extracts from each abstract before analysis. The system clusters these claims across years into an interactive map where every trend traces back to the claims and papers behind it. Applied to six years of EMNLP, it shows the field shifting away from classic NLP tasks toward LLM-era capabilities such as reasoning and multimodality — a movement that keyword or whole-abstract counts blur. The released data extend beyond EMNLP: the same pipeline has processed the full ACL Anthology (346k claims, 80k abstracts, 423 venues). Extraction is human-validated and clustering checked against an external manually constructed taxonomy.