排序
标签

ReflectRec: Cycle-Consistency Preference Verification for LLM-based Recommendation
CoT-style LLM recommenders generate a natural-language preference note as a chain-of-thought prefix to ranking, but the note is trusted without verification, and the ranker never consults behaviorally...

Coverage Governs Accuracy: When to Expand the Lexicon and When to Fall Back in Low-Resource Manchu OCR
Character-level OCR for low-resource Manchu often produces near-miss spelling errors. Lexicon-constrained decoding can correct such errors with lexical knowledge, but a fixed dictionary cannot cover t...

NarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative Decoding
Speculative decoding is widely used to speed up generation in large language models (LLMs), with a small draft model proposing tokens that one forward pass of the target model verifies. Draft models t...

Beyond Replacement: Levenshtein Editing for Diffusion Language Models
Diffusion language models (DLMs) offer a flexible alternative to autoregressive models, enabling any-order infilling. While most existing decoding methods treat decoded tokens as fixed, some recent mo...

FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs
Asking a model to check retrieved text can also tell it which source to trust. We introduce FutureBench, a renewable framework for evaluating knowledge-context conflict using timestamped questions, co...

Can LLMs Understand What They Predict? Evaluating Latent Causal Structure Inference in Financial Markets
Large language models (LLMs) are increasingly evaluated through their ability to predict future outcomes, implicitly assuming that predictive success reflects an understanding of the underlying system...

From Arraignment to Resolution: Transformer Models of Court Cases
The criminal legal system is composed of many complex decision points, such as which charges are pursued, how bond is determined, plea deal negotiations, and sentencing. Given the profound impact of s...

Tracking Representations in LLM Reasoning Traces for Iterated Games
Large language model (LLM) agents achieve state-of-the-art performance across domains through chain-of-thought (CoT) reasoning. Despite their ubiquitous use, little is understood about the relationshi...

Chorus: Shared N-gram Embeddings with Layer-wise Adaptation
Language models can gain capacity at little computational cost from n-gram embedding tables: large tables of learned vectors for short sequences of consecutive tokens, which are looked up and added to...

Prioritize, Don't Decide: What We Learned Auditing a Deployed Human-in-the-Loop CV Sorter
A single academic vacancy can draw hundreds of applications, and the first screening round consumes most of a committee's time. We describe a CV Priority Sorter deployed at a national platform for aca...

AI Will Not Make You Rich (2025)
The disruption is real. It's also predictable.

Elon Musk tries to explain what’s going on with Ukraine and Starlink
加载中...
已经到底啦