Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation is difficult because natural-language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthetic grade-school mat...
Ratish Puduppully, Pranabendu Misra, Paarth Iyer et al.· 0 citations
Bias auditing should be treated as an ongoing, multi-vendor process, rather than a one-time assessment, because gender-related biases are common in LLMs, but their direction and magnitude are highly heterogeneous, to the point that some models behave in diametrically opposite ways to others.
E. Bolzoni, Valerio Capraro· arXiv.org· 1 citation
On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD treats all teacher signals equally, assuming that the teacher's supervision is equally important for every token. However, teacher signals at different tokens may have v...
Zhen-Yu Wang, Tian-Ze Wang, Lin-Jun Zhang et al.· 0 citations
We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, coverage-first packet compilation, and deterministic reasoning scaffolds; an LLM is used only as a replaceable final reader. The chain places all gold sessions in the candidat...
Christopher J. Chanhnourack· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
AccHMR, the accuracy multiplied by HMR, which reports the reward in proportion to the accuracy, is proposed, which reports the reward in proportion to the accuracy, and on which the revised rules would have scored 0.6549, 5th.
Julien Knafou, L. Mottin, Alexandre Flament et al.· 0 citations
This work is the first to unveil the critical role of the null space and harness it for model optimization, and uses a simplified analytical model about optimization to demonstrate why null-space can effectively reduce attention entropy, thereby improving the efficiency of reasoning.
Hong-Bo Ma, Sansheng Cao, Jia-Jun Fan et al.· 0 citations
PUMBA is introduced, a unified framework for trajectory-aware training that trains the denoiser on consecutive steps of policy-induced trajectories, passes information between steps, and optimizes them jointly by backpropagation through time.
Manuel Madeira, Amitis Shidani, Alice Bizeul et al.· arXiv.org· 2 citations· ⚡1
This work uses training data attribution to quantitatively estimate how much each harmful example contributes to EM and benchmark the quality of the attribution via retraining -- a sound attribution score should enable us to enhance or attenuate EM by filtering data on that score.
Gonçalo Paulo, Louis Jaburi, Nora Belrose et al.· 1 citation
GRAFT (Gated Replacement of Answer-Failed groups with peer Trajectories), an off-policy-aware framework that replaces all-fail groups with informative peer groups and transfers both successful and unsuccessful peer responses with peer-computed advantages, while controlling cross-model mismatch through sequence-level co...
Doohyuk Jang, Y. Park, Gyouk Chu et al.· arXiv.org· 0 citations
MIST, the Misleading-Image Stress Test: 200 English sentences, each built around a phrase readable either figuratively or literally and shown with an aligned image depicting its reading, a misleading image depicting the opposite, or no image at all is introduced.
Nagham Omar, Mahmoud Jabarin, Kinan Ibraheem et al.· 0 citations
LoopSLM builds on looped Transformers for latent reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass, and further narrows the perception-reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT.
Sheng-Bo Cai, Yu-Xiang Wang, Jing-Ran Xie et al.· 2 citations
We propose a rubric for assessing expressed clinical reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART, SCT, Key Feature Problems and OSCE); clinical LLM benchmarks (MedR-Bench, HealthBench, TIMER-Bench, DR. BENCH, PrIME-LLM and PatientSafeBench); and general LL...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
