Related papers: CORE: Collaborative Reasoning via Cross Teaching

Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…

Recent work on enhancing the reasoning abilities of large language models (LLMs) has introduced explicit length control as a means of constraining computational cost while preserving accuracy. However, existing approaches rely on…

Recommender systems trained on offline historical user behaviors are embracing conversational techniques to online query user preference. Unlike prior conversational recommendation approaches that systemically combine conversational and…

Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmarks primarily evaluate final output correctness under a…

Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by…

Self-correction has demonstrated potential in code generation by allowing language models to revise and improve their outputs through successive refinement. Recent studies have explored prompting-based strategies that incorporate…

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

Robots are increasingly operating in open-world environments where safe behavior depends on context: the same hallway may require different navigation strategies when crowded versus empty, or during an emergency versus normal operations.…

We present ACCORD, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop counterfactuals. ACCORD introduces formal elements to…

Large Language Models (LLMs), despite their remarkable capabilities, rely on singular, pre-dominant reasoning paradigms, hindering their performance on intricate problems that demand diverse cognitive strategies. To address this, we…

Large language models (LLMs) struggle in knowledge-intensive tasks, as retrievers often overfit to surface similarity and fail on queries involving complex logical relations. The capacity for logical analysis is inherent in model…

Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on…

The fundamental success of large language models hinges upon the efficacious implementation of large-scale distributed training techniques. Nevertheless, building a vast, high-performance cluster featuring high-speed communication…

Deep Learning (DL) models to analyze source code have shown immense promise during the past few years. More recently, self-supervised pre-training has gained traction for learning generic code representations valuable for many downstream SE…

Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an…

Millions of users come to online peer counseling platforms to seek support. However, studies show that online peer support groups are not always as effective as expected, largely due to users' negative experiences with unhelpful counselors.…

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…

While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical…

Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. However, in many reasoning domains, the model must also validate generated tasks and…

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…