Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.
Ishan Jindal, Sai Prashanth Akuthota, Jayant Taneja, and SACHIN DEV SHARMA
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
Prefix consistency weights CoT answers by their regeneration frequency from truncated prefixes and reaches standard self-consistency accuracy at a median 4.6x fewer tokens across five models and four benchmarks.
RLCM trains LLMs with a margin-enhanced process reward that widens the gap between correct and incorrect reasoning steps, improving calibration on math, code, logic, and science tasks without hurting accuracy.
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
citing papers explorer
-
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.
-
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
-
Reliable Chain-of-Thought via Prefix Consistency
Prefix consistency weights CoT answers by their regeneration frequency from truncated prefixes and reaches standard self-consistency accuracy at a median 4.6x fewer tokens across five models and four benchmarks.
-
Process Supervision of Confidence Margin for Calibrated LLM Reasoning
RLCM trains LLMs with a margin-enhanced process reward that widens the gap between correct and incorrect reasoning steps, improving calibration on math, code, logic, and science tasks without hurting accuracy.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.