LLM-Evaluation

TL;DR for operators IndoBias is a useful paper because it attacks a lazy assumption: that a model becomes fairer in a country once it becomes more fluent in that country’s language. Charming idea. Unfortunately, culture is not a plugin. The paper introduces a two-track benchmark for bias in Indonesian and three local languages: Javanese, Sundanese, and Makasar. The first track, IndoBias-Pairs, uses 544 contrastive stereotype pairs per language to test whether a model assigns higher likelihood to prototypical statements than to counter-stereotypical ones. The second track, IndoBias-QA, uses generation-based prompts across 336 demographic groups to examine stereotype polarity at broader coverage, including groups that may not have widely agreed stereotype pairs. ...

TL;DR for operators AI systems are getting better at producing outputs that look structured: code, CAD, diagrams, workflows, compliance memos, procurement recommendations, and decision traces. That is not the same as keeping the structure right. Two recent arXiv papers make this point from opposite ends of the problem. One looks inside language models and finds evidence for a compact retrieval-conditioned rebinding mechanism: the model does not necessarily rewrite its whole internal world after a state change; it can preserve old representations and redirect retrieval when the answer is needed.1 The other builds an engineering benchmark for Text-to-CAD and shows that models can pass earlier surface gates — executable code, plausible geometry — while still failing the practical tests of functionality, manufacturability, and assemblability.2 ...

TL;DR for operators A frontier LLM judge is an expensive way to inspect every agent trajectory for reward hacking. This paper asks whether a much smaller detector can do most of that monitoring job at much lower cost. The answer is: yes, under the same information condition, and with important caveats. A 13.8M-parameter transformer encoder plus a logistic regression probe detects reward hacking in cleaned Terminal-Wrench trajectories with 0.9467 AUC and 0.8296 TPR@5%FPR. In the authors’ matched comparison, a reproduced gpt-5.4 judge reaches 0.9510 AUC and 0.7130 TPR@5%FPR on the cleaned sanitized-vs-baseline split.1 ...

TL;DR for operators NICE is useful because it does not ask whether a model has “social intelligence” as one grand, vaguely flattering trait. It breaks social intelligence into a diagnostic structure: 4 categories, 11 dimensions, 34 facets, and 137 Chinese-context ranking items. That matters because a model can look socially competent in aggregate while failing on the interaction behaviours that make or break real deployments. ...

The procurement meeting is where public leaderboards go to look useful Benchmark scores are comforting because they compress chaos into a number. One model is 87.3, another is 84.9, and suddenly the procurement meeting has the emotional texture of financial discipline. Very mature. Very measurable. Also, very possibly irrelevant. The problem is simple. A company rarely wants “the best model on average”. It wants the best model for contract review, support triage, clinical note summarisation, SQL repair, claims handling, product search, or whatever unglamorous workflow actually pays the cloud bill. Public benchmarks are often too generic for that decision. Worse, the benchmark items may already be floating inside model training data, turning evaluation into a memory test with better typography. ...

Trust is a bad deployment strategy. That is not a moral statement. It is an operations statement. In most enterprise AI workflows, the uncomfortable question is not “Can the model answer?” The model will answer. Models are generous like that. The question is whether the organization has a reliable way to notice when the answer is unsupported, fabricated, overconfident, or merely polished nonsense wearing a tie. ...

Enterprise AI has developed two favorite comfort blankets: the model’s confident explanation and the benchmark score. The first says, “Relax, I reasoned through this.” The second says, “Relax, I scored well on a public test.” Both are useful. Neither is a warranty. And when business teams treat either as proof of reliability, the result is not governance. It is theatre with better typography. ...

A good analyst should occasionally try to break their own idea. Not performatively. Not with a decorative “on the other hand” paragraph. Actually break it. Ask the kind of question that could make the current hypothesis collapse, then watch whether the evidence forces a better one. That simple discipline is the center of FalsifyBench: Evaluating Inductive Reasoning in LLMs with Rule Discovery Games, a new paper by Leonardo Bertolazzi, Katya Tentori, and Raffaella Bernardi.1 The paper is framed around scientific reasoning, but its practical message travels well beyond science. If an AI agent cannot test outside its own current belief, it may look careful while doing something much less impressive: confirming the first plausible story it invented. ...

Right Answer, Wrong Audit: When Reasoning Models Grade the Destination, Not the Route A reviewer sees the final number. It is correct. Then the quiet failure begins. The reviewer stops asking whether the argument actually works. The missing step becomes “implicit.” The shuffled logic becomes “not ideal, but acceptable.” The circular explanation becomes “verbose but essentially correct.” The answer has done something worse than persuade. It has anesthetized the audit. ...

A customer-support bot gives a fluent answer. The grammar is clean, the tone is helpful, and the confidence is offensively calm. Then someone checks the underlying fact and discovers the answer is wrong. The old operating question was: Was the model confident? The better question is: What did the model’s uncertainty look like while it was speaking? ...