Related papers: Parallel Belief Revision via Order Aggregation

Related papers

Retrieval Needs Multivectors: An Exponential Separation [14.201575154107294]
We introduce ANDOR, a new retrieval benchmark that naturally instantiates these hard examples.<n>We show that state-of-the-art single-vector embedding models perform poorly on ANDOR in the zero-shot setting.<n>In contrast, multi-vector models consistently outperform their single-vector counterparts and improve substantially with fine-tuning.
arXiv Detail & Related papers (2026-08-21T13:26:44Z)
Claim Plane: Enforceable Change Intents and Dynamic Scope for Parallel Coding Agents [1.4721615285883427]
This paper presents Claim Plane, a model-agnostic coordination architecture that treats concurrent software change as a pre-write admission problem.<n>A deterministic control plane atomically admits compatible intents, constrains same-file parallelism to declared regions, serializes unresolved overlap, tracks dependency invalidation, and fails closed on ambiguous authority.<n>During execution, a contingent mutation does not reserve write ownership initially; the first attempted mutation triggers atomic scope promotion and re-admission against the current active set.
arXiv Detail & Related papers (2026-07-24T02:30:50Z)
RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation [52.23179023639867]
Sequential recommender systems rely on a single forward pass to encode user interaction and predict the next item.<n>How to structure the reasoning process for sequential recommendation remains an open question.<n>Existing approaches couple reasoning and prediction in a single $d$-dimensional state, limiting reasoning depth.<n>We propose RecRec (Recursive Reasoning for Recommendation), an RL-free framework that overcomes fixed $d$-dimensional state of methods.
arXiv Detail & Related papers (2026-07-14T16:28:28Z)
Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction [0.0]
This study proposes a structured framework combining parallel chunk-level processing with evidence-anchored consolidation.<n>Experiments with multiple model types and sizes indicate that parallel processing significantly reduces omission error by approximately 84%.<n>Smaller models benefited most, suggesting that efficient parallel chunking and consolidation play a critical role in achieving reliable and scalable textual analysis.
arXiv Detail & Related papers (2026-04-04T05:11:20Z)
PRISM: Parallel Residual Iterative Sequence Model [52.26239951489612]
We propose PRISM (Parallel Residual Iterative Sequence Model) to resolve this tension.<n>PRISM introduces a solver-inspired inductive bias that captures key structural properties of multi-step refinement in a parallelizable form.<n>We prove that this formulation achieves Rank-$L$ accumulation, structurally expanding the update manifold beyond the single-step Rank-$1$ bottleneck.
arXiv Detail & Related papers (2026-02-11T12:39:41Z)
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing [76.48164395646019]
Parallel-Probe is a training-free controller designed to optimize online parallel thinking.<n>It reduces sequential tokens by up to $textbf35.8$% and total token cost by over $textbf25.8$% while maintaining competitive accuracy.
arXiv Detail & Related papers (2026-02-03T18:59:41Z)
Parallel Context-of-Experts Decoding for Retrieval Augmented Generation [11.887068025002362]
We propose a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding.<n>We propose Parallel Context-of-Experts Decoding (Pced), a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding.
arXiv Detail & Related papers (2026-01-13T15:46:59Z)
A Survey on Parallel Reasoning [58.66122129692264]
We first present a formal definition of parallel reasoning and clarify its distinction from related concepts like Chain-of-Thought.<n>We then organize and discuss advanced techniques based on a novel taxonomy, including non-interactive reasoning, interactive reasoning, and efficiency-focused decoding strategies.<n>We highlight the core challenges of parallel reasoning and suggest potential directions for future research.
arXiv Detail & Related papers (2025-10-14T05:42:19Z)
Rethinking Thinking Tokens: LLMs as Improvement Operators [80.12087211785949]
Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which allows them to explore solution strategies with self-checking.<n>This results in higher accuracy, but inflates context length, token/compute cost, and answer latency.<n>We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier?<n>We identify an interesting inference family Parallel-Distill-Refine (PDR), which performs the following: (i) generate diverse drafts in parallel; (ii) distill them into a bounded, textual workspace; and (iii) refine conditioned on this workspace
arXiv Detail & Related papers (2025-10-01T17:08:59Z)
FoldA: Computing Partial-Order Alignments Using Directed Net Unfoldings [0.6906005491572401]
This paper proposes a new technique for computing partial-order alignments on the fly using directed Petri net unfoldings, named FoldA.<n>We evaluate our technique on 485 synthetic model-log pairs and compare it against Astar- and Dijkstra-alignments on 13 real-life model-log pairs and 6 benchmark pairs.
arXiv Detail & Related papers (2025-06-10T09:44:05Z)
Parallel Belief Contraction via Order Aggregation [1.474723404975345]
We consider how to extend serial contraction operations that obey stronger properties.<n>We also consider the iterated case: the behaviour of beliefs after a sequence of parallel contractions.<n>We propose a general method for extending serial iterated belief change operators to handle parallel change.
arXiv Detail & Related papers (2025-01-23T00:42:16Z)
Consecutive Batch Model Editing with HooK Layers [59.673084839708224]
CoachHooK is a model editing method that simultaneously supports sequential and batch editing. It is memory-friendly as it only needs a small amount of it to store several hook layers whose size remains unchanged over time.
arXiv Detail & Related papers (2024-03-08T14:07:44Z)
Vanishing Feature: Diagnosing Model Merging and Beyond [1.1510009152620668]
We identify the vanishing feature'' phenomenon, where input-induced features diminish during propagation through a merged model.<n>We show that existing normalization strategies can be enhanced by precisely targeting the vanishing feature issue.<n>We propose the Preserve-First Merging'' (PFM) strategy, which focuses on preserving early-layer features.
arXiv Detail & Related papers (2024-02-05T17:06:26Z)
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction [28.205723817300576]
Document pair extraction aims to identify key and value entities as well as their relationships from visually-rich documents. Most existing methods divide it into two separate tasks: semantic entity recognition (SER) and relation extraction (RE) This paper introduces a novel framework, PEneo, which performs document pair extraction in a unified pipeline.
arXiv Detail & Related papers (2024-01-07T12:48:07Z)
HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision [118.0818807474809]
This work proposes a principled, probabilistic approach for training explainable multi-hop QA systems without rationale supervision. Our approach performs multi-hop reasoning by explicitly modeling rationales as sets, enabling the model to capture interactions between documents and sentences within a document.
arXiv Detail & Related papers (2023-05-23T16:53:49Z)
A Critique of Strictly Batch Imitation Learning [26.121994149869767]
We argue that notational issues obscure how the psuedo-state visitation distribution might be disconnected from the policy's $textittrue$ state visitation distribution. We construct examples where the parameter coupling advocated by Jarrett et al. leads to inconsistent estimates of the expert's policy, unlike behavioral cloning.
arXiv Detail & Related papers (2021-10-05T14:07:30Z)
Joint Passage Ranking for Diverse Multi-Answer Retrieval [56.43443577137929]
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a question. This task requires joint modeling of retrieved passages, as models should not repeatedly retrieve passages containing the same answer at the cost of missing a different valid answer. In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. To model the joint probability of the retrieved passages, JPR makes use of an autoregressive reranker that selects a sequence of passages, equipped with novel training and decoding algorithms.
arXiv Detail & Related papers (2021-04-17T04:48:36Z)
The Extraordinary Failure of Complement Coercion Crowdsourcing [50.599433903377374]
Crowdsourcing has eased and scaled up the collection of linguistic annotation in recent years. We aim to collect annotated data for this phenomenon by reducing it to either of two known tasks: Explicit Completion and Natural Language Inference. In both cases, crowdsourcing resulted in low agreement scores, even though we followed the same methodologies as in previous work.
arXiv Detail & Related papers (2020-10-12T19:04:04Z)
Incomplete Utterance Rewriting as Semantic Segmentation [57.13577518412252]
We present a novel and extensive approach, which formulates it as a semantic segmentation task. Instead of generating from scratch, such a formulation introduces edit operations and shapes the problem as prediction of a word-level edit matrix. Our approach is four times faster than the standard approach in inference.
arXiv Detail & Related papers (2020-09-28T09:29:49Z)
Iterative Edit-Based Unsupervised Sentence Simplification [30.128553647491817]
Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. We iteratively perform word and phrase-level edits on the complex sentence.
arXiv Detail & Related papers (2020-06-17T03:53:12Z)
Lower bounds in multiple testing: A framework based on derandomized proxies [107.69746750639584]
This paper introduces an analysis strategy based on derandomization, illustrated by applications to various concrete models. We provide numerical simulations of some of these lower bounds, and show a close relation to the actual performance of the Benjamini-Hochberg (BH) algorithm.
arXiv Detail & Related papers (2020-05-07T19:59:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.