Update README.md

README.md

@@ -101,11 +101,11 @@ but without explicitly answering the query or suggesting a solution.
 
 Extract:
 
-- **Buffer A**: 10-15 words from the Top-5 ranked documents and query itself, strongly associated with the query.
+- **Buffer A**: 10-15 words from the Top-5 ranked documents and the query itself, strongly associated with the query.
 
 **Generate an adversarial sentences** that satisfy ALL the following:
 
-- Include combination of words (at least 5) or similar words (similar embedding) from Buffer A** that is most related to the query and help promote ranking significantly and integrates well with Target Document
+- Include a combination of words (at least 5) or similar words (similar embedding) from Buffer A** that is most related to the query and help promote ranking significantly and integrates well with Target Document
 - DO NOT use the words that answer the query.
 - Are **fluent**, **grammatically sound**, and **consistent with the style** of the Target Document.
 - **Do NOT answer, suggest, or hint at an answer to the Target Query**.
@@ -165,7 +165,7 @@ Recommended decoding settings:
 For adversarial attack or robust candidate selection, we recommend a generate-then-rank approach:
 
 1. Generate a pool of candidates (≈10) with the same decoding settings (top_p=0.95, temperature=0.6).
-2. Score each candidate using an embedding-based surrogate with BERT base uncased (`google-bert/bert-base-uncased`). Compute cosine similarity between the query and each candidate and pick the highest.
+2. Score each candidate using a surrogate model e.g. BERT base uncased (`google-bert/bert-base-uncased`). Compute cosine similarity between the query and each candidate and pick the highest.
 3. Select the highest-scoring candidate as the final output.
 
 This pool-plus-ranking approach tends to improve robustness for adversarial objectives.